Recent works imply that the channel pruning can be regarded as searching optimal sub-structure from unpruned networks.

However, existing works based on this observation require training and evaluating a large number of structures, which limits their application.

In this paper, we propose a novel differentiable method for channel pruning, named Differentiable Markov Channel Pruning (DMCP), to efficiently search the optimal sub-structure.

Our method is differentiable and can be directly optimized by gradient descent with respect to standard task loss and budget regularization (e.g. FLOPs constraint).

In DMCP, we model the channel pruning as a Markov process, in which each state represents for retaining the corresponding channel during pruning, and transitions between states denote the pruning process.

In the end, our method is able to implicitly select the proper number of channels in each layer by the Markov process with optimized transitions. To validate the effectiveness of our method, we perform extensive experiments on Imagenet with ResNet and MobilenetV2.

Results show our method can achieve consistent improvement than state-of-the-art pruning methods in various FLOPs settings. The code is available at https://github.com/zx55/dmcp

We study the problem of pricing under a Multinomial Logit model where we incorporate network effects over the consumer's decisions. We analyse both cases, when sellers compete or collaborate. In particular, we pay special attention to the overall expected revenue and how the behaviour of the no purchase option is affected under variations of a network effect parameter. Where for example we prove that the market share for the no purchase option, is decreasing in terms of the value of the network effect, meaning that stronger communication among costumers increases the expected amount of sales. We also analyse how the customer's utility is altered when network effects are incorporated into the market, comparing the cases where both competitive and monopolistic prices are displayed. We use tools from stochastic approximation algorithms to prove that the probability of purchasing the available products converges to a unique stationary distribution. We model that the sellers can use this stationary distribution to establish their strategies. Finding that under those settings, a pure Nash Equilibrium represents the pricing strategies in the case of competition, and an optimal (that maximises the total revenue) fixed price characterise the case of collaboration.

The paper develops a robotic manipulation system to treat the pressing needs for handling a large number of test tubes in clinical examination and replace or reduce human labor. It presents the technical details of the system, which separates and arranges test tubes in racks with the help of 3D vision and artificial intelligence (AI) reasoning/planning. The developed system only requires a person to put a rack with mixed and non-arranged tubes in front of a robot. The robot autonomously performs recognition, reasoning, planning, manipulation, etc., and returns a rack with separated and arranged tubes. The system is simple-to-use, and there are no requests for expert knowledge in robotics. We expect such a system to play an important role in helping managing public health and hope similar systems could be extended to other clinical manipulation like handling mixers and pipettes in the future.

Most studies on speaker verification systems focus on long-duration utterances, which are composed of sufficient phonetic information. However, the performances of these systems are known to degrade when short-duration utterances are inputted due to the lack of phonetic information as compared to the long utterances. In this paper, we propose a method that compensates for the performance degradation of speaker verification for short utterances, referred to as "crop aggregating". The proposed method adopts an ensemble-based design to improve the stability and accuracy of speaker verification systems. The proposed method segments an input utterance into several short utterances and then aggregates the segment embeddings extracted from the segmented inputs to compose a speaker embedding. Then, this method simultaneously trains the segment embeddings and the aggregated speaker embedding. In addition, we also modified the teacher-student learning method for the proposed method. Experimental results on different input duration using the VoxCeleb1 test set demonstrate that the proposed technique improves speaker verification performance by about 45.37% relatively compared to the baseline system with 1-second test utterance condition.

A big part of the video content we consume from video providers consists of genres featuring low-light aesthetics. Low light sequences have special characteristics, such as spatio-temporal varying acquisition noise and light flickering, that make the encoding process challenging. To deal with the spatio-temporal incoherent noise, higher bitrates are used to achieve high objective quality. Additionally, the quality assessment metrics and methods have not been designed, trained or tested for this type of content. This has inspired us to trigger research in that area and propose a Grand Challenge on encoding low-light video sequences. In this paper, we present an overview of the proposed challenge, and test state-of-the-art methods that will be part of the benchmark methods at the stage of the participants' deliverable assessment. From this exploration, our results show that VVC already achieves a high performance compared to simply denoising the video source prior to encoding. Moreover, the quality of the video streams can be further improved by employing a post-processing image enhancement method.

Data analytics in the cloud has become an integral part of enterprise businesses. Big data analytics systems, however, still lack the ability to take user performance goals and budgetary constraints for a task, collectively referred to as task objectives, and automatically configure an analytic job to achieve these objectives. This paper presents a data analytics optimizer that can automatically determine a cluster configuration with a suitable number of cores as well as other system parameters that best meet the task objectives. At a core of our work is a principled multi-objective optimization (MOO) approach that computes a Pareto optimal set of job configurations to reveal tradeoffs between different user objectives, recommends a new job configuration that best explores such tradeoffs, and employs novel optimizations to enable such recommendations within a few seconds. We present efficient incremental algorithms based on the notion of a Progressive Frontier for realizing our MOO approach and implement them into a Spark-based prototype. Detailed experiments using benchmark workloads show that our MOO techniques provide a 2-50x speedup over existing MOO methods, while offering good coverage of the Pareto frontier. When compared to Ottertune, a state-of-the-art performance tuning system, our approach recommends configurations that yield 26\%-49\% reduction of running time of the TPCx-BB benchmark while adapting to different application preferences on multiple objectives.

Reinforcement learning methods have been used to compute dialog policies from language-based interaction experiences. Efficiency is of particular importance in dialog policy learning, because of the considerable cost of interacting with people, and the very poor user experience from low-quality conversations. Aiming at improving the efficiency of dialog policy learning, we develop algorithm LHUA (Learning with Hindsight, User modeling, and Adaptation) that, for the first time, enables dialog agents to adaptively learn with hindsight from both simulated and real users. Simulation and hindsight provide the dialog agent with more experience and more (positive) reinforcements respectively. Experimental results suggest that, in success rate and policy quality, LHUA outperforms competitive baselines from the literature, including its no-simulation, no-adaptation, and no-hindsight counterparts.

Fashion trend forecasting is a crucial task for both academia and industry. Although some efforts have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal the real fashion trends. Towards insightful fashion trend forecasting, this work focuses on investigating fine-grained fashion element trends for specific user groups. We first contribute a large-scale fashion trend dataset (FIT) collected from Instagram with extracted time series fashion element records and user information. Further-more, to effectively model the time series data of fashion elements with rather complex patterns, we propose a Knowledge EnhancedRecurrent Network model (KERN) which takes advantage of the capability of deep recurrent neural networks in modeling time-series data. Moreover, it leverages internal and external knowledge in fashion domain that affects the time-series patterns of fashion element trends. Such incorporation of domain knowledge further enhances the deep learning model in capturing the patterns of specific fashion elements and predicting the future trends. Extensive experiments demonstrate that the proposed KERN model can effectively capture the complicated patterns of objective fashion elements, therefore making preferable fashion trend forecast.

While the exact definition and implementation of accountability depend on the specific context, at its core accountability describes a mechanism that will make decisions transparent and often provides means to sanction "bad" decisions. As such, accountability is specifically relevant for Cyber-Physical Systems, such as robots or drones, that embed themselves into a human society, take decisions and might cause lasting harm. Without a notion of accountability, such systems could behave with impunity and would not fit into society. Despite its relevance, there is currently no agreement on its meaning and, more importantly, no way to express accountability properties for these systems. As a solution we propose to express the accountability properties of systems using Structural Causal Models. They can be represented as human-readable graphical models while also offering mathematical tools to analyze and reason over them. Our central contribution is to show how Structural Causal Models can be used to express and analyze the accountability properties of systems and that this approach allows us to identify accountability patterns. These accountability patterns can be catalogued and used to improve systems and their architectures.

Automated person re-identification in a multi-camera surveillance setup is very important for effective tracking and monitoring crowd movement. In the recent years, few deep learning based re-identification approaches have been developed which are quite accurate but time-intensive, and hence not very suitable for practical purposes. In this paper, we propose an efficient hierarchical re-identification approach in which color histogram based comparison is first employed to find the closest matches in the gallery set, and next deep feature based comparison is carried out using Siamese network. Reduction in search space after the first level of matching helps in achieving a fast response time as well as improving the accuracy of prediction by the Siamese network by eliminating vastly dissimilar elements. A silhouette part-based feature extraction scheme is adopted in each level of hierarchy to preserve the relative locations of the different body structures and make the appearance descriptors more discriminating in nature. The proposed approach has been evaluated on five public data sets and also a new data set captured by our team in our laboratory. Results reveal that it outperforms most state-of-the-art approaches in terms of overall accuracy.

Software Defined Networking is currently revolutionizing computer networking by decoupling the network control (control plane) from the forwarding functions (data plane) enabling the network control to become directly programmable and the underlying infrastructure to be abstracted for applications and network services. Next to the well-known OpenFlow protocol, the XML-based NETCONF protocol is also an important means for exchanging configuration information from a management platform and is nowadays even part of OpenFlow. In combination with NETCONF, YANG is the corresponding protocol that defines the associated data structures supporting virtually all network configuration protocols. YANG itself is a semantically rich language, which -- in order to facilitate familiarization with the relevant subject -- is often visualized to involve other experts or developers and to support them by their daily work (writing applications which make use of YANG). In order to support this process, this paper presents an novel approach to optimize and simplify YANG data models to assist further discussions with the management and implementations (especially of interfaces) to reduce complexity. Therefore, we have defined a bidirectional mapping of YANG to UML and developed a tool that renders the created UML diagrams. This combines the benefits to use the formal language YANG with automatically maintained UML diagrams to involve other experts or developers, closing the gap between technically improved data models and their human readability.

Multi-view data capture permits free-viewpoint video (FVV) content creation. To this end, several users must capture video streams, calibrated in both time and pose, framing the same object/scene, from different viewpoints. New-generation network architectures (e.g. 5G) promise lower latency and larger bandwidth connections supported by powerful edge computing, properties that seem ideal for reliable FVV capture. We have explored this possibility, aiming to remove the need for bespoke synchronisation hardware when capturing a scene from multiple viewpoints, making it possible through off-the-shelf mobiles. We propose a novel and scalable data capture architecture that exploits edge resources to synchronise and harvest frame captures. We have designed an edge computing unit that supervises the relaying of timing triggers to and from multiple mobiles, in addition to synchronising frame harvesting. We empirically show the benefits of our edge computing unit by analysing latencies and show the quality of 3D reconstruction outputs against an alternative and popular centralised solution based on Unity3D.

In this paper we analyze a continuous version of the maximal covering location problem, in which the facilities are required to be interconnected by means of a graph structure in which two facilities are allowed to be linked if a given distance is not exceed. We provide a mathematical programming framework for the problem and different resolution strategies. First, we propose a Mixed Integer Non Linear Programming formulation, and derive properties of the problem that allow us to project the continuous variables out avoiding the nonlinear constraints, resulting in an equivalent pure integer programming formulation. Since the number of constraints in the integer programming formulation is large and the constraints are, in general, difficult to handle, we propose two branch-&-cut approaches that avoid the complete enumeration of the constraints resulting in more efficient procedures. We report the results of an extensive battery of computational experiments comparing the performance of the different approaches.

Learning-based techniques are increasingly effective at controlling complex systems using data-driven models. However, most work done so far has focused on learning individual tasks or control laws. Hence, it is still a largely unaddressed research question how multiple tasks can be learned efficiently and simultaneously on the same system. In particular, no efficient state space exploration schemes have been designed for multi-task control settings. Using this research gap as our main motivation, we present an algorithm that approximates the smallest data set that needs to be collected in order to achieve high control performance for multiple learning-based control laws. We describe system uncertainty using a probabilistic Gaussian process model, which allows us to quantify the impact of potentially collected data on each learning-based controller. We then determine the optimal measurement locations by solving a stochastic optimization problem approximately. We show that, under reasonable assumptions, the approximate solution converges towards that of the exact problem. Additionally, we provide a numerical illustration of the proposed algorithm.

This paper considers a convex optimization problem with cost and constraints that evolve over time. The function to be minimized is strongly convex and possibly non-differentiable, and variables are coupled through linear constraints.In this setting, the paper proposes an online algorithm based on the alternating direction method of multipliers(ADMM), to track the optimal solution trajectory of the time-varying problem; in particular, the proposed algorithm consists of a primal proximal gradient descent step and an appropriately perturbed dual ascent step. The paper derives tracking results, asymptotic bounds, and linear convergence results. The proposed algorithm is then specialized to a multi-area power grid optimization problem, and our numerical results verify the desired properties.

Visualization-oriented natural language interfaces (V-NLIs) have been explored and developed in recent years. One challenge faced by V-NLIs is in the formation of effective design decisions that usually requires a deep understanding of user queries. Learning-based approaches have shown potential in V-NLIs and reached state-of-the-art performance in various NLP tasks. However, because of the lack of sufficient training samples that cater to visual data analytics, cutting-edge techniques have rarely been employed to facilitate the development of V-NLIs. We present a new dataset, called Quda, to help V-NLIs understand free-form natural language. Our dataset contains 14;035 diverse user queries annotated with 10 low-level analytic tasks that assist in the deployment of state-of-the-art techniques for parsing complex human language. We achieve this goal by first gathering seed queries with data analysts who are target users of V-NLIs. Then we employ extensive crowd force for paraphrase generation and validation. We demonstrate the usefulness of Quda in building V-NLIs by creating a prototype that makes effective design decisions for free-form user queries. We also show that Quda can be beneficial for a wide range of applications in the visualization community by analyzing the design tasks described in academic publications.

A method for encoding information in DNA sequences is described. The method is based on the precision-resolution framework, and is aimed to work in conjunction with a recently suggested terminator-free template independent DNA synthesis method. The suggested method optimizes the amount of information bits per synthesis time unit, namely, the writing rate. Additionally, the encoding scheme studied here takes into account the existence of multiple copies of the DNA sequence, which are independently distorted. Finally, quantizers for various run-length distributions are designed.

Selecting an appropriate model to forecast product demand is critical to the manufacturing industry. However, due to the data complexity, market uncertainty and users' demanding requirements for the model, it is challenging for demand analysts to select a proper model. Although existing model selection methods can reduce the manual burden to some extent, they often fail to present model performance details on individual products and reveal the potential risk of the selected model. This paper presents DFSeer, an interactive visualization system to conduct reliable model selection for demand forecasting based on the products with similar historical demand. It supports model comparison and selection with different levels of details. Besides, it shows the difference in model performance on similar products to reveal the risk of model selection and increase users' confidence in choosing a forecasting model. Two case studies and interviews with domain experts demonstrate the effectiveness and usability of DFSeer.

Software development has been changing rapidly. This development process can be influenced through changing developer friendly approaches. We can save time consumption and accelerate the development process if we can automatically guide programmer during software development. There are some approaches that recommended relevant code snippets and APIitems to the developer. Some approaches apply general code, searching techniques and some approaches use an online based repository mining strategies. But it gets quite difficult to help programmers when they need particular type conversion problems. More specifically when they want to adapt existing interfaces according to their expectation. One of the familiar triumph to guide developers in such situation is adapting collections and arrays through automated adaptation of object ensembles. But how does it help to a novice developer in real time software development that is not explicitly specified? In this paper, we have developed a system that works as a plugin-tool integrated with a particular Data Mining Integrated environment (DMIE) to recommend relevant interface while they seek for a type conversion situation. We have a mined repository of respective adapter classes and related APIs from where developer, search their query and get their result using the relevant transformer classes. The system that recommends developers titled automated objective ensembles (AOE plugin).From the investigation as we have ever made, we can see that our approach much better than some of the existing approaches.

High-order entropy-stable discontinuous Galerkin (DG) methods for nonlinear conservation laws reproduce a discrete entropy inequality by combining entropy conservative finite volume fluxes with summation-by-parts (SBP) discretization matrices. In the DG context, on tensor product (quadrilateral and hexahedral) elements, SBP matrices are typically constructed by collocating at Lobatto quadrature points. Recent work has extended the construction of entropy-stable DG schemes to collocation at more accurate Gauss quadrature points.

In this work, we extend entropy-stable Gauss collocation schemes to non-conforming meshes. Entropy-stable DG schemes require computing entropy conservative numerical fluxes between volume and surface quadrature nodes. On conforming tensor product meshes where volume and surface nodes are aligned, flux evaluations are required only between "lines" of nodes. However, on non-conforming meshes, volume and surface nodes are no longer aligned, resulting in a larger number of flux evaluations. We reduce this expense by introducing an entropy-stable mortar-based treatment of non-conforming interfaces via a face-local correction term, and provide necessary conditions for high-order accuracy. Numerical experiments in both two and three dimensions confirm the stability and accuracy of this approach.

An important goal in reinforcement learning is to create agents that can quickly adapt to new goals while avoiding situations that might cause damage to themselves or their environments. One way agents learn is through exploration mechanisms, which are needed to discover new policies. However, in deep reinforcement learning, exploration is normally done by injecting noise in the action space. While performing well in many domains, this setup has the inherent risk that the noisy actions performed by the agent lead to unsafe states in the environment. Here we introduce a novel approach called Meta-Learned Instinctual Networks (MLIN) that allows agents to safely learn during their lifetime while avoiding potentially hazardous states. At the core of the approach is a plastic network trained through reinforcement learning and an evolved "instinctual" network, which does not change during the agent's lifetime but can modulate the noisy output of the plastic network. We test our idea on a simple 2D navigation task with no-go zones, in which the agent has to learn to approach new targets during deployment. MLIN outperforms standard meta-trained networks and allows agents to learn to navigate to new targets without colliding with any of the no-go zones. These results suggest that meta-learning augmented with an instinctual network is a promising new approach for safe AI, which may enable progress in this area on a variety of different domains.

Water quality has a direct impact on industry, agriculture, and public health. Algae species are common indicators of water quality. It is because algal communities are sensitive to changes in their habitats, giving valuable knowledge on variations in water quality. However, water quality analysis requires professional inspection of algal detection and classification under microscopes, which is very time-consuming and tedious. In this paper, we propose a novel multi-target deep learning framework for algal detection and classification. Extensive experiments were carried out on a large-scale colored microscopic algal dataset. Experimental results demonstrate that the proposed method leads to the promising performance on algal detection, class identification and genus identification.

Spiking neural networks (SNNs) are considered as a potential candidate to overcome current challenges such as the high-power consumption encountered by artificial neural networks (ANNs), however there is still a gap between them with respect to the recognition accuracy on practical tasks. A conversion strategy was thus introduced recently to bridge this gap by mapping a trained ANN to an SNN. However, it is still unclear that to what extent this obtained SNN can benefit both the accuracy advantage from ANN and high efficiency from the spike-based paradigm of computation. In this paper, we propose two new conversion methods, namely TerMapping and AugMapping. The TerMapping is a straightforward extension of a typical threshold-balancing method with a double-threshold scheme, while the AugMapping additionally incorporates a new scheme of augmented spike that employs a spike coefficient to carry the number of typical all-or-nothing spikes occurring at a time step. We examine the performance of our methods based on MNIST, Fashion-MNIST and CIFAR10 datasets. The results show that the proposed double-threshold scheme can effectively improve accuracies of the converted SNNs. More importantly, the proposed AugMapping is more advantageous for constructing accurate, fast and efficient deep SNNs as compared to other state-of-the-art approaches. Our study therefore provides new approaches for further integration of advanced techniques in ANNs to improve the performance of SNNs, which could be of great merit to applied developments with spike-based neuromorphic computing.

Bayesian predictive coding is a putative neuromorphic method for acquiring higher-level neural representations to account for sensory input. Although originating in the neuroscience community, there are also efforts in the machine learning community to study these models. This paper reviews some of the more well known models. Our review analyzes module connectivity and patterns of information transfer, seeking to find general principles used across the models. We also survey some recent attempts to cast these models within a deep learning framework. A defining feature of Bayesian predictive coding is that it uses top-down, reconstructive mechanisms to predict incoming sensory inputs or their lower-level representations. Discrepancies between the predicted and the actual inputs, known as prediction errors, then give rise to future learning that refines and improves the predictive accuracy of learned higher-level representations. Predictive coding models intended to describe computations in the neocortex emerged prior to the development of deep learning and used a communication structure between modules that we name the Rao-Ballard protocol. This protocol was derived from a Bayesian generative model with some rather strong statistical assumptions. The RB protocol provides a rubric to assess the fidelity of deep learning models that claim to implement predictive coding.

Recently, the outbreak of Coronavirus Disease 2019 (COVID-19) has spread rapidly across the world. Due to the large number of affected patients and heavy labor for doctors, computer-aided diagnosis with machine learning algorithm is urgently needed, and could largely reduce the efforts of clinicians and accelerate the diagnosis process. Chest computed tomography (CT) has been recognized as an informative tool for diagnosis of the disease. In this study, we propose to conduct the diagnosis of COVID-19 with a series of features extracted from CT images. To fully explore multiple features describing CT images from different views, a unified latent representation is learned which can completely encode information from different aspects of features and is endowed with promising class structure for separability. Specifically, the completeness is guaranteed with a group of backward neural networks (each for one type of features), while by using class labels the representation is enforced to be compact within COVID-19/community-acquired pneumonia (CAP) and also a large margin is guaranteed between different types of pneumonia. In this way, our model can well avoid overfitting compared to the case of directly projecting highdimensional features into classes. Extensive experimental results show that the proposed method outperforms all comparison methods, and rather stable performances are observed when varying the numbers of training data.

Segmentation is a prerequisite yet challenging task for medical image analysis. In this paper, we introduce a novel deeply supervised active learning approach for finger bones segmentation. The proposed architecture is fine-tuned in an iterative and incremental learning manner. In each step, the deep supervision mechanism guides the learning process of hidden layers and selects samples to be labeled. Extensive experiments demonstrated that our method achieves competitive segmentation results using less labeled samples as compared with full annotation.

Over the years, performance evaluation has become essential in computer vision, enabling tangible progress in many sub-fields. While talking-head video generation has become an emerging research topic, existing evaluations on this topic present many limitations. For example, most approaches use human subjects (e.g., via Amazon MTurk) to evaluate their research claims directly. This subjective evaluation is cumbersome, unreproducible, and may impend the evolution of new research. In this work, we present a carefully-designed benchmark for evaluating talking-head video generation with standardized dataset pre-processing strategies. As for evaluation, we either propose new metrics or select the most appropriate ones to evaluate results in what we consider as desired properties for a good talking-head video, namely, identity preserving, lip synchronization, high video quality, and natural-spontaneous motion. By conducting a thoughtful analysis across several state-of-the-art talking-head generation approaches, we aim to uncover the merits and drawbacks of current methods and point out promising directions for future work. All the evaluation code is available at: https://github.com/lelechen63/talking-head-generation-survey.

Inspired by Bitcoin, many different kinds of cryptocurrencies based on blockchain technology have turned up on the market. Due to the special structure of the blockchain, it has been deemed impossible to directly trade between traditional currencies and cryptocurrencies or between different types of cryptocurrencies. Generally, trading between different currencies is conducted through a centralized third-party platform. However, it has the problem of a single point of failure, which is vulnerable to attacks and thus affects the security of the transactions. In this paper, we propose a distributed cryptocurrency trading scheme to solve the problem of centralized exchanges, which can achieve trading between different types of cryptocurrencies. Our scheme is implemented with smart contracts on the Ethereum blockchain and deployed on the Ethereum test network. We not only implement transactions between individual users, but also allow transactions between multiple users. The experimental result proves that the cost of our scheme is acceptable.

Artificial intelligence technology has made its way absolutely necessary in a variety of industries including the fitness industry. Human pose estimation is one of the important researches in the field of Computer Vision for the last few years. In this project, pose estimation and deep machine learning techniques are combined to analyze the performance and report feedback on the repetitions of performed exercises in real-time. Involving machine learning technology in the fitness industry could help the judges to count repetitions of any exercise during Weightlifting or CrossFit competitions.

We analyze the computational complexity of motion planning through local "input/output" gadgets with separate entrances and exits, and a subset of allowed traversals from entrances to exits, each of which changes the state of the gadget and thereby the allowed traversals. We study such gadgets in the 0-, 1-, and 2-player settings, in particular extending past motion-planning-through-gadgets work to 0-player games for the first time, by considering "branchless" connections between gadgets that route every gadget's exit to a unique gadget's entrance. Our complexity results include containment in L, NL, P, NP, and PSPACE; as well as hardness for NL, P, NP, and PSPACE. We apply these results to show PSPACE-completeness for certain mechanics in Factorio, [the Sequence], and a restricted version of Trainyard, improving prior results. This work strengthens prior results on switching graphs and reachability switching games.

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel CNN-RNN-transducer architecture, which we call ContextNet. ContextNet features a fully convolutional encoder that incorporates global context information into convolution layers by adding squeeze-and-excitation modules. In addition, we propose a simple scaling method that scales the widths of ContextNet that achieves good trade-off between computation and accuracy. We demonstrate that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate (WER) of 2.1\%/4.6\% without external language model (LM), 1.9\%/4.1\% with LM and 2.9\%/7.0\% with only 10M parameters on the clean/noisy LibriSpeech test sets. This compares to the previous best published system of 2.0\%/4.6\% with LM and 3.9\%/11.3\% with 20M parameters. The superiority of the proposed ContextNet model is also verified on a much larger internal dataset.

We show that the traveling salesman problem (TSP) and its many variants may be modeled as functional optimization problems over a graph. In this formulation, all vertices and arcs of the graph are functionals; i.e., a mapping from a space of measurable functions to the field of real numbers. Many variants of the TSP, such as those with neighborhoods, with forbidden neighborhoods, with time-windows and with profits, can all be framed under this construct. In sharp contrast to their discrete-optimization counterparts, the modeling constructs presented in this paper represent a fundamentally new domain of analysis and computation for TSPs and their variants. Beyond its apparent mathematical unification of a class of problems in graph theory, the main advantage of the new approach is that it facilitates the modeling of certain application-specific problems in their home space of measurable functions. Consequently, certain elements of economic system theory such as dynamical models and continuous-time cost/profit functionals can be directly incorporated in the new optimization problem formulation. Furthermore, subtour elimination constraints, prevalent in discrete optimization formulations, are naturally enforced through continuity requirements. The price for the new modeling framework is nonsmooth functionals. Although a number of theoretical issues remain open in the proposed mathematical framework, we demonstrate the computational viability of the new modeling constructs over a sample set of problems to illustrate the rapid production of end-to-end TSP solutions to extensively-constrained practical problems.

We consider the problem of protecting and manipulating elections by recounting and changing ballots, respectively. Our setting involves a plurality-based election held across multiple districts, and the problem formulations are based on the model proposed recently by~[Elkind et al, IJCAI 2019]. It turns out that both of the manipulation and protection problems are NP-complete even in fairly simple settings. We study these problems from a parameterized perspective with the goal of establishing a more detailed complexity landscape. The parameters we consider include the number of voters, and the budgets of the attacker and the defender. While we observe fixed-parameter tractability when parameterizing by number of voters, our main contribution is a demonstration of parameterized hardness when working with the budgets of the attacker and the defender.

Fact-based dialogue generation is a task of generating a human-like response based on both dialogue context and factual texts. Various methods were proposed to focus on generating informative words that contain facts effectively. However, previous works implicitly assume a topic to be kept on a dialogue and usually converse passively, therefore the systems have a difficulty to generate diverse responses that provide meaningful information proactively. This paper proposes an end-to-end Fact-based dialogue system augmented with the ability of convergent and divergent thinking over both context and facts, which can converse about the current topic or introduce a new topic. Specifically, our model incorporates a novel convergent and divergent decoding that can generate informative and diverse responses considering not only given inputs (context and facts) but also inputs-related topics. Both automatic and human evaluation results on DSTC7 dataset show that our model significantly outperforms state-of-the-art baselines, indicating that our model can generate more appropriate, informative, and diverse responses.

We identify the structure of the lexicographically least word avoiding 5/4-powers on the alphabet of nonnegative integers. Specifically, we show that this word has the form $p au(varphi(z) varphi^2(z) cdots)$ where $p, z$ are finite words, $varphi$ is a 6-uniform morphism, and $ au$ is a coding. This description yields a recurrence for the $i$th letter, which we use to prove that the sequence of letters is 6-regular with rank 188. More generally, we prove $k$-regularity for a sequence satisfying a recurrence of the same type.

Pandemic measures such as social distancing and contact tracing can be enhanced by rapidly integrating dynamic location data and demographic data. Projecting billions of longitude and latitude locations onto hundreds of thousands of highly irregular demographic census block polygons is computationally challenging in both research and deployment contexts. This paper describes two approaches labeled "simple" and "fast". The simple approach can be implemented in any scripting language (Matlab/Octave, Python, Julia, R) and is easily integrated and customized to a variety of research goals. This simple approach uses a novel combination of hierarchy, sparse bounding boxes, polygon crossing-number, vectorization, and parallel processing to achieve 100,000,000+ projections per second on 100 servers. The simple approach is compact, does not increase data storage requirements, and is applicable to any country or region. The fast approach exploits the thread, vector, and memory optimizations that are possible using a low-level language (C++) and achieves similar performance on a single server. This paper details these approaches with the goal of enabling the broader community to quickly integrate location and demographic data.

This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. The challenge was divided into two tracks. Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image. Track 2 focused on the burst demoireing problem, where a set of degraded moire images of the same scene were provided as input, with the goal of producing a single demoired image as output. The methods were ranked in terms of their fidelity, measured using the peak signal-to-noise ratio (PSNR) between the ground truth clean images and the restored images produced by the participants' methods. The tracks had 142 and 99 registered participants, respectively, with a total of 14 and 6 submissions in the final testing stage. The entries span the current state-of-the-art in image and burst image demoireing problems.

We propose an augmented Lagrangian preconditioner for a three-field stress-velocity-pressure discretization of stationary non-Newtonian incompressible flow with an implicit constitutive relation of power-law type. The discretization employed makes use of the divergence-free Scott-Vogelius pair for the velocity and pressure. The preconditioner builds on the work [P. E. Farrell, L. Mitchell, and F. Wechsung, SIAM J. Sci. Comput., 41 (2019), pp. A3073-A3096], where a Reynolds-robust preconditioner for the three-dimensional Newtonian system was introduced. The preconditioner employs a specialized multigrid method for the stress-velocity block that involves a divergence-capturing space decomposition and a custom prolongation operator. The solver exhibits excellent robustness with respect to the parameters arising in the constitutive relation, allowing for the simulation of a wide range of materials.

We study the problem of jointly designing a sparse sensor and actuator schedule for linear dynamical systems while guaranteeing a control/estimation performance that approximates the fully sensed/actuated setting. We further prove a separation principle, showing that the problem can be decomposed into finding sensor and actuator schedules separately. However, it is shown that this problem cannot be efficiently solved or approximated in polynomial, or even quasi-polynomial time for time-invariant sensor/actuator schedules; instead, we develop deterministic polynomial-time algorithms for a time-varying sensor/actuator schedule with guaranteed approximation bounds. Our main result is to provide a polynomial-time joint actuator and sensor schedule that on average selects only a constant number of sensors and actuators at each time step, irrespective of the dimension of the system. The key idea is to sparsify the controllability and observability Gramians while providing approximation guarantees for Hankel singular values. This idea is inspired by recent results in theoretical computer science literature on sparsification.

In this technical report we give an elementary introduction to Quantum Computing for non-physicists. In this introduction we describe in detail some of the foundational Quantum Algorithms including: the Deutsch-Jozsa Algorithm, Shor's Algorithm, Grocer Search, and Quantum Counting Algorithm and briefly the Harrow-Lloyd Algorithm. Additionally we give an introduction to Solomonoff Induction, a theoretically optimal method for prediction. We then attempt to use Quantum computing to find better algorithms for the approximation of Solomonoff Induction. This is done by using techniques from other Quantum computing algorithms to achieve a speedup in computing the speed prior, which is an approximation of Solomonoff's prior, a key part of Solomonoff Induction. The major limiting factors are that the probabilities being computed are often so small that without a sufficient (often large) amount of trials, the error may be larger than the result. If a substantial speedup in the computation of an approximation of Solomonoff Induction can be achieved through quantum computing, then this can be applied to the field of intelligent agents as a key part of an approximation of the agent AIXI.

Monitoring users on large computing platforms such as high performance computing (HPC) and cloud computing systems is non-trivial. Utilities such as process viewers provide limited insight into what users are running, due to granularity limitation, and other sources of data, such as system call tracing, can impose significant operational overhead. However, despite technical and procedural measures, instances of users abusing valuable HPC resources for personal gains have been documented in the past cite{hpcbitmine}, and systems that are open to large numbers of loosely-verified users from around the world are at risk of abuse. In this paper, we show how electrical power consumption data from an HPC platform can be used to identify what programs are executed. The intuition is that during execution, programs exhibit various patterns of CPU and memory activity. These patterns are reflected in the power consumption of the system and can be used to identify programs running. We test our approach on an HPC rack at Lawrence Berkeley National Laboratory using a variety of scientific benchmarks. Among other interesting observations, our results show that by monitoring the power consumption of an HPC rack, it is possible to identify if particular programs are running with precision up to and recall of 95\% even in noisy scenarios.

Neural networks have opened up many new opportunities to utilize remotely sensed images in meteorology. Common applications include image classification, e.g., to determine whether an image contains a tropical cyclone, and image translation, e.g., to emulate radar imagery for satellites that only have passive channels. However, there are yet many open questions regarding the use of neural networks in meteorology, such as best practices for evaluation, tuning and interpretation. This article highlights several strategies and practical considerations for neural network development that have not yet received much attention in the meteorological community, such as the concept of effective receptive fields, underutilized meteorological performance measures, and methods for NN interpretation, such as synthetic experiments and layer-wise relevance propagation. We also consider the process of neural network interpretation as a whole, recognizing it as an iterative scientist-driven discovery process, and breaking it down into individual steps that researchers can take. Finally, while most work on neural network interpretation in meteorology has so far focused on networks for image classification tasks, we expand the focus to also include networks for image translation.

We introduce a variant of PCPs, that we refer to as rectangular PCPs, wherein proofs are thought of as square matrices, and the random coins used by the verifier can be partitioned into two disjoint sets, one determining the row of each query and the other determining the *column*.

We construct PCPs that are efficient, short, smooth and (almost-)rectangular. As a key application, we show that proofs for hard languages in NTIME$(2^n)$, when viewed as matrices, are rigid infinitely often. This strengthens and considerably simplifies a recent result of Alman and Chen [FOCS, 2019] constructing explicit rigid matrices in FNP. Namely, we prove the following theorem: - There is a constant $delta in (0,1)$ such that there is an FNP-machine that, for infinitely many $N$, on input $1^N$ outputs $N imes N$ matrices with entries in $mathbb{F}_2$ that are $delta N^2$-far (in Hamming distance) from matrices of rank at most $2^{log N/Omega(log log N)}$.

Our construction of rectangular PCPs starts with an analysis of how randomness yields queries in the Reed--Muller-based outer PCP of Ben-Sasson, Goldreich, Harsha, Sudan and Vadhan [SICOMP, 2006; CCC, 2005]. We then show how to preserve rectangularity under PCP composition and a smoothness-inducing transformation. This warrants refined and stronger notions of rectangularity, which we prove for the outer PCP and its transforms.

Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora only. However, it is still challenging to associate source-target sentences in the latent space. As people speak different languages biologically share similar visual systems, the potential of achieving better alignment through visual content is promising yet under-explored in unsupervised multimodal MT (MMT). In this paper, we investigate how to utilize visual content for disambiguation and promoting latent space alignment in unsupervised MMT. Our model employs multimodal back-translation and features pseudo visual pivoting in which we learn a shared multilingual visual-semantic embedding space and incorporate visually-pivoted captioning as additional weak supervision. The experimental results on the widely used Multi30K dataset show that the proposed model significantly improves over the state-of-the-art methods and generalizes well when the images are not available at the testing time.

We consider generic optimal Bayesian inference, namely, models of signal reconstruction where the posterior distribution and all hyperparameters are known. Under a standard assumption on the concentration of the free energy, we show how replica symmetry in the strong sense of concentration of all multioverlaps can be established as a consequence of the Franz-de Sanctis identities; the identities themselves in the current setting are obtained via a novel perturbation of the prior distribution of the signal. Concentration of multioverlaps means that asymptotically the posterior distribution has a particularly simple structure encoded by a random probability measure (or, in the case of binary signal, a non-random probability measure). We believe that such strong control of the model should be key in the study of inference problems with underlying sparse graphical structure (error correcting codes, block models, etc) and, in particular, in the derivation of replica symmetric formulas for the free energy and mutual information in this context.

Smart meters enable remote and automatic electricity, water and gas consumption reading and are being widely deployed in developed countries. Nonetheless, there is still a huge number of non-smart meters in operation. Image-based Automatic Meter Reading (AMR) focuses on dealing with this type of meter readings. We estimate that the Energy Company of Paran'a (Copel), in Brazil, performs more than 850,000 readings of dial meters per month. Those meters are the focus of this work. Our main contributions are: (i) a public real-world dial meter dataset (shared upon request) called UFPR-ADMR; (ii) a deep learning-based recognition baseline on the proposed dataset; and (iii) a detailed error analysis of the main issues present in AMR for dial meters. To the best of our knowledge, this is the first work to introduce deep learning approaches to multi-dial meter reading, and perform experiments on unconstrained images. We achieved a 100.0% F1-score on the dial detection stage with both Faster R-CNN and YOLO, while the recognition rates reached 93.6% for dials and 75.25% for meters using Faster R-CNN (ResNext-101).

Feature pyramid has been an efficient method to extract features at different scales. Development over this method mainly focuses on aggregating contextual information at different levels while seldom touching the inter-level correlation in the feature pyramid. Early computer vision methods extracted scale-invariant features by locating the feature extrema in both spatial and scale dimension. Inspired by this, a convolution across the pyramid level is proposed in this study, which is termed pyramid convolution and is a modified 3-D convolution. Stacked pyramid convolutions directly extract 3-D (scale and spatial) features and outperforms other meticulously designed feature fusion modules. Based on the viewpoint of 3-D convolution, an integrated batch normalization that collects statistics from the whole feature pyramid is naturally inserted after the pyramid convolution. Furthermore, we also show that the naive pyramid convolution, together with the design of RetinaNet head, actually best applies for extracting features from a Gaussian pyramid, whose properties can hardly be satisfied by a feature pyramid. In order to alleviate this discrepancy, we build a scale-equalizing pyramid convolution (SEPC) that aligns the shared pyramid convolution kernel only at high-level feature maps. Being computationally efficient and compatible with the head design of most single-stage object detectors, the SEPC module brings significant performance improvement ($>4$AP increase on MS-COCO2017 dataset) in state-of-the-art one-stage object detectors, and a light version of SEPC also has $sim3.5$AP gain with only around 7% inference time increase. The pyramid convolution also functions well as a stand-alone module in two-stage object detectors and is able to improve the performance by $sim2$AP. The source code can be found at https://github.com/jshilong/SEPC.

Narrowband internet-of-things (NB-IoT) is a competitive 5G technology for massive machine-type communication scenarios, but meanwhile introduces narrowband interference (NBI) to existing broadband transmission such as the long term evolution (LTE) systems in enhanced mobile broadband (eMBB) scenarios. In order to facilitate the harmonic and fair coexistence in wireless heterogeneous networks, it is important to eliminate NB-IoT interference to LTE systems. In this paper, a novel sparse machine learning based framework and a sparse combinatorial optimization problem is formulated for accurate NBI recovery, which can be efficiently solved using the proposed iterative sparse learning algorithm called sparse cross-entropy minimization (SCEM). To further improve the recovery accuracy and convergence rate, regularization is introduced to the loss function in the enhanced algorithm called regularized SCEM. Moreover, exploiting the spatial correlation of NBI, the framework is extended to multiple-input multiple-output systems. Simulation results demonstrate that the proposed methods are effective in eliminating NB-IoT interference to LTE systems, and significantly outperform the state-of-the-art methods.

The interoperability of proof assistants and the integration of their libraries is a highly valued but elusive goal in the field of theorem proving. As a preparatory step, in previous work, we translated the libraries of multiple proof assistants, specifically the ones of Coq, HOL Light, IMPS, Isabelle, Mizar, and PVS into a universal format: OMDoc/MMT.

Each translation presented tremendous theoretical, technical, and social challenges, some universal and some system-specific, some solvable and some still open. In this paper, we survey these challenges and compare and evaluate the solutions we chose.

We believe similar library translations will be an essential part of any future system interoperability solution and our experiences will prove valuable to others undertaking such efforts.

Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions, explore the given environments, and reach the desired target locations. These step-by-step navigational instructions are crucial when the agent is navigating new environments about which it has no prior knowledge. Most recent works that study VLN observe a significant performance drop when tested on unseen environments (i.e., environments not used in training), indicating that the neural agent models are highly biased towards training environments. Although this issue is considered as one of the major challenges in VLN research, it is still under-studied and needs a clearer explanation. In this work, we design novel diagnosis experiments via environment re-splitting and feature replacement, looking into possible reasons for this environment bias. We observe that neither the language nor the underlying navigational graph, but the low-level visual appearance conveyed by ResNet features directly affects the agent model and contributes to this environment bias in results. According to this observation, we explore several kinds of semantic representations that contain less low-level visual information, hence the agent learned with these features could be better generalized to unseen testing environments. Without modifying the baseline agent model and its training method, our explored semantic features significantly decrease the performance gaps between seen and unseen on multiple datasets (i.e. R2R, R4R, and CVDN) and achieve competitive unseen results to previous state-of-the-art models. Our code and features are available at: https://github.com/zhangybzbo/EnvBiasVLN