October 20, 2019

3232 words 16 mins read

Paper Group ANR 50

Combinatorial Multi-Objective Multi-Armed Bandit Problem. Optimal and Low-Complexity Dynamic Spectrum Access for RF-Powered Ambient Backscatter System with Online Reinforcement Learning. Image Reconstruction Using Deep Learning. Enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing. k-SVRG: Varia …

Combinatorial Multi-Objective Multi-Armed Bandit Problem


Title	Combinatorial Multi-Objective Multi-Armed Bandit Problem
Authors	Doruk Öner, Altuğ Karakurt, Atilla Eryılmaz, Cem Tekin
Abstract	In this paper, we introduce the COmbinatorial Multi-Objective Multi-Armed Bandit (COMO-MAB) problem that captures the challenges of combinatorial and multi-objective online learning simultaneously. In this setting, the goal of the learner is to choose an action at each time, whose reward vector is a linear combination of the reward vectors of the arms in the action, to learn the set of super Pareto optimal actions, which includes the Pareto optimal actions and actions that become Pareto optimal after adding an arbitrary small positive number to their expected reward vectors. We define the Pareto regret performance metric and propose a fair learning algorithm whose Pareto regret is $O(N L^3 \log T)$, where $T$ is the time horizon, $N$ is the number of arms and $L$ is the maximum number of arms in an action. We show that COMO-MAB has a wide range of applications, including recommending bundles of items to users and network routing, and focus on a resource-allocation application for multi-user communication in the presence of multidimensional performance metrics, where we show that our algorithm outperforms existing MAB algorithms.
Tasks
Published	2018-03-11
URL	http://arxiv.org/abs/1803.04039v1
PDF	http://arxiv.org/pdf/1803.04039v1.pdf
PWC	https://paperswithcode.com/paper/combinatorial-multi-objective-multi-armed
Repo
Framework

Optimal and Low-Complexity Dynamic Spectrum Access for RF-Powered Ambient Backscatter System with Online Reinforcement Learning


Title	Optimal and Low-Complexity Dynamic Spectrum Access for RF-Powered Ambient Backscatter System with Online Reinforcement Learning
Authors	Nguyen Van Huynh, Dinh Thai Hoang, Diep N. Nguyen, Eryk Dutkiewicz, Dusit Niyato, Ping Wang
Abstract	Ambient backscatter has been introduced with a wide range of applications for low power wireless communications. In this article, we propose an optimal and low-complexity dynamic spectrum access framework for RF-powered ambient backscatter system. In this system, the secondary transmitter not only harvests energy from ambient signals (from incumbent users), but also backscatters these signals to its receiver for data transmission. Under the dynamics of the ambient signals, we first adopt the Markov decision process (MDP) framework to obtain the optimal policy for the secondary transmitter, aiming to maximize the system throughput. However, the MDP-based optimization requires complete knowledge of environment parameters, e.g., the probability of a channel to be idle and the probability of a successful packet transmission, that may not be practical to obtain. To cope with such incomplete knowledge of the environment, we develop a low-complexity online reinforcement learning algorithm that allows the secondary transmitter to “learn” from its decisions and then attain the optimal policy. Simulation results show that the proposed learning algorithm not only efficiently deals with the dynamics of the environment, but also improves the average throughput up to 50% and reduces the blocking probability and delay up to 80% compared with conventional methods.
Tasks
Published	2018-09-08
URL	http://arxiv.org/abs/1809.02753v1
PDF	http://arxiv.org/pdf/1809.02753v1.pdf
PWC	https://paperswithcode.com/paper/optimal-and-low-complexity-dynamic-spectrum
Repo
Framework

Image Reconstruction Using Deep Learning


Title	Image Reconstruction Using Deep Learning
Authors	Po-Yu Liu, Edmund Y. Lam
Abstract	This paper proposes a deep learning architecture that attains statistically significant improvements over traditional algorithms in Poisson image denoising espically when the noise is strong. Poisson noise commonly occurs in low-light and photon- limited settings, where the noise can be most accurately modeled by the Poission distribution. Poisson noise traditionally prevails only in specific fields such as astronomical imaging. However, with the booming market of surveillance cameras, which commonly operate in low-light environments, or mobile phones, which produce noisy night scene pictures due to lower-grade sensors, the necessity for an advanced Poisson image denoising algorithm has increased. Deep learning has achieved amazing breakthroughs in other imaging problems, such image segmentation and recognition, and this paper proposes a deep learning denoising network that outperforms traditional algorithms in Poisson denoising especially when the noise is strong. The architecture incorporates a hybrid of convolutional and deconvolutional layers along with symmetric connections. The denoising network achieved statistically significant 0.38dB, 0.68dB, and 1.04dB average PSNR gains over benchmark traditional algorithms in experiments with image peak values 4, 2, and 1. The denoising network can also operate with shorter computational time while still outperforming the benchmark algorithm by tuning the reconstruction stride sizes.
Tasks	Denoising, Image Denoising, Image Reconstruction, Semantic Segmentation
Published	2018-09-27
URL	http://arxiv.org/abs/1809.10410v1
PDF	http://arxiv.org/pdf/1809.10410v1.pdf
PWC	https://paperswithcode.com/paper/image-reconstruction-using-deep-learning
Repo
Framework

Enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing


Title	Enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing
Authors	Jiangjun Peng, Qi Xie, Qian Zhao, Yao Wang, Deyu Meng, Yee Leung
Abstract	The 3-D total variation (3DTV) is a powerful regularization term, which encodes the local smoothness prior structure underlying a hyper-spectral image (HSI), for general HSI processing tasks. This term is calculated by assuming identical and independent sparsity structures on all bands of gradient maps calculated along spatial and spectral HSI modes. This, however, is always largely deviated from the real cases, where the gradient maps are generally with different while correlated sparsity structures across all their bands. Such deviation tends to hamper the performance of the related method by adopting such prior term. To this is- sue, this paper proposes an enhanced 3DTV (E-3DTV) regularization term beyond conventional 3DTV. Instead of imposing sparsity on gradient maps themselves, the new term calculated sparsity on the subspace bases on the gradient maps along their bands, which naturally encode the correlation and difference across these bands, and more faithfully reflect the insightful configurations of an HSI. The E-3DTV term can easily replace the previous 3DTV term and be em- bedded into an HSI processing model to ameliorate its performance. The superiority of the proposed methods is substantiated by extensive experiments on two typical related tasks: HSI denoising and compressed sensing, as compared with state-of-the-arts designed for both tasks.
Tasks	Denoising, Image Denoising
Published	2018-09-18
URL	http://arxiv.org/abs/1809.06591v1
PDF	http://arxiv.org/pdf/1809.06591v1.pdf
PWC	https://paperswithcode.com/paper/enhanced-3dtv-regularization-and-its
Repo
Framework

k-SVRG: Variance Reduction for Large Scale Optimization


Title	k-SVRG: Variance Reduction for Large Scale Optimization
Authors	Anant Raj, Sebastian U. Stich
Abstract	Variance reduced stochastic gradient (SGD) methods converge significantly faster than the vanilla SGD counterpart. However, these methods are not very practical on large scale problems, as they either i) require frequent passes over the full data to recompute gradients—without making any progress during this time (like for SVRG), or ii)~they require additional memory that can surpass the size of the input problem (like for SAGA). In this work, we propose $k$-SVRG that addresses these issues by making best use of the \emph{available} memory and minimizes the stalling phases without progress. We prove linear convergence of $k$-SVRG on strongly convex problems and convergence to stationary points on non-convex problems. Numerical experiments show the effectiveness of our method.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00982v2
PDF	http://arxiv.org/pdf/1805.00982v2.pdf
PWC	https://paperswithcode.com/paper/k-svrg-variance-reduction-for-large-scale
Repo
Framework

Low-Rank Embedding of Kernels in Convolutional Neural Networks under Random Shuffling


Title	Low-Rank Embedding of Kernels in Convolutional Neural Networks under Random Shuffling
Authors	Chao Li, Zhun Sun, Jinshi Yu, Ming Hou, Qibin Zhao
Abstract	Although the convolutional neural networks (CNNs) have become popular for various image processing and computer vision task recently, it remains a challenging problem to reduce the storage cost of the parameters for resource-limited platforms. In the previous studies, tensor decomposition (TD) has achieved promising compression performance by embedding the kernel of a convolutional layer into a low-rank subspace. However the employment of TD is naively on the kernel or its specified variants. Unlike the conventional approaches, this paper shows that the kernel can be embedded into more general or even random low-rank subspaces. We demonstrate this by compressing the convolutional layers via randomly-shuffled tensor decomposition (RsTD) for a standard classification task using CIFAR-10. In addition, we analyze how the spatial similarity of the training data influences the low-rank structure of the kernels. The experimental results show that the CNN can be significantly compressed even if the kernels are randomly shuffled. Furthermore, the RsTD-based method yields more stable classification accuracy than the conventional TD-based methods in a large range of compression ratios.
Tasks
Published	2018-10-31
URL	http://arxiv.org/abs/1810.13098v1
PDF	http://arxiv.org/pdf/1810.13098v1.pdf
PWC	https://paperswithcode.com/paper/low-rank-embedding-of-kernels-in
Repo
Framework

Hardware-Aware Machine Learning: Modeling and Optimization


Title	Hardware-Aware Machine Learning: Modeling and Optimization
Authors	Diana Marculescu, Dimitrios Stamoulis, Ermao Cai
Abstract	Recent breakthroughs in Deep Learning (DL) applications have made DL models a key component in almost every modern computing system. The increased popularity of DL applications deployed on a wide-spectrum of platforms have resulted in a plethora of design challenges related to the constraints introduced by the hardware itself. What is the latency or energy cost for an inference made by a Deep Neural Network (DNN)? Is it possible to predict this latency or energy consumption before a model is trained? If yes, how can machine learners take advantage of these models to design the hardware-optimal DNN for deployment? From lengthening battery life of mobile devices to reducing the runtime requirements of DL models executing in the cloud, the answers to these questions have drawn significant attention. One cannot optimize what isn’t properly modeled. Therefore, it is important to understand the hardware efficiency of DL models during serving for making an inference, before even training the model. This key observation has motivated the use of predictive models to capture the hardware performance or energy efficiency of DL applications. Furthermore, DL practitioners are challenged with the task of designing the DNN model, i.e., of tuning the hyper-parameters of the DNN architecture, while optimizing for both accuracy of the DL model and its hardware efficiency. Therefore, state-of-the-art methodologies have proposed hardware-aware hyper-parameter optimization techniques. In this paper, we provide a comprehensive assessment of state-of-the-art work and selected results on the hardware-aware modeling and optimization for DL applications. We also highlight several open questions that are poised to give rise to novel hardware-aware designs in the next few years, as DL applications continue to significantly impact associated hardware systems and platforms.
Tasks
Published	2018-09-14
URL	http://arxiv.org/abs/1809.05476v1
PDF	http://arxiv.org/pdf/1809.05476v1.pdf
PWC	https://paperswithcode.com/paper/hardware-aware-machine-learning-modeling-and
Repo
Framework

Algorithms for Estimating Trends in Global Temperature Volatility


Title	Algorithms for Estimating Trends in Global Temperature Volatility
Authors	Arash Khodadadi, Daniel J McDonald
Abstract	Trends in terrestrial temperature variability are perhaps more relevant for species viability than trends in mean temperature. In this paper, we develop methodology for estimating such trends using multi-resolution climate data from polar orbiting weather satellites. We derive two novel algorithms for computation that are tailored for dense, gridded observations over both space and time. We evaluate our methods with a simulation that mimics these data’s features and on a large, publicly available, global temperature dataset with the eventual goal of tracking trends in cloud reflectance temperature variability.
Tasks
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07376v2
PDF	http://arxiv.org/pdf/1805.07376v2.pdf
PWC	https://paperswithcode.com/paper/algorithms-for-estimating-trends-in-global
Repo
Framework

Exploring to learn visual saliency: The RL-IAC approach


Title	Exploring to learn visual saliency: The RL-IAC approach
Authors	Celine Craye, Timothee Lesort, David Filliat, Jean-Francois Goudou
Abstract	The problem of object localization and recognition on autonomous mobile robots is still an active topic. In this context, we tackle the problem of learning a model of visual saliency directly on a robot. This model, learned and improved on-the-fly during the robot’s exploration provides an efficient tool for localizing relevant objects within their environment. The proposed approach includes two intertwined components. On the one hand, we describe a method for learning and incrementally updating a model of visual saliency from a depth-based object detector. This model of saliency can also be exploited to produce bounding box proposals around objects of interest. On the other hand, we investigate an autonomous exploration technique to efficiently learn such a saliency model. The proposed exploration, called Reinforcement Learning-Intelligent Adaptive Curiosity (RL-IAC) is able to drive the robot’s exploration so that samples selected by the robot are likely to improve the current model of saliency. We then demonstrate that such a saliency model learned directly on a robot outperforms several state-of-the-art saliency techniques, and that RL-IAC can drastically decrease the required time for learning a reliable saliency model.
Tasks	Object Localization
Published	2018-04-02
URL	http://arxiv.org/abs/1804.00435v1
PDF	http://arxiv.org/pdf/1804.00435v1.pdf
PWC	https://paperswithcode.com/paper/exploring-to-learn-visual-saliency-the-rl-iac
Repo
Framework

Whetstone: A Method for Training Deep Artificial Neural Networks for Binary Communication


Title	Whetstone: A Method for Training Deep Artificial Neural Networks for Binary Communication
Authors	William Severa, Craig M. Vineyard, Ryan Dellana, Stephen J. Verzi, James B. Aimone
Abstract	This paper presents a new technique for training networks for low-precision communication. Targeting minimal communication between nodes not only enables the use of emerging spiking neuromorphic platforms, but may additionally streamline processing conventionally. Low-power and embedded neuromorphic processors potentially offer dramatic performance-per-Watt improvements over traditional von Neumann processors, however programming these brain-inspired platforms generally requires platform-specific expertise which limits their applicability. To date, the majority of artificial neural networks have not operated using discrete spike-like communication. We present a method for training deep spiking neural networks using an iterative modification of the backpropagation optimization algorithm. This method, which we call Whetstone, effectively and reliably configures a network for a spiking hardware target with little, if any, loss in performance. Whetstone networks use single time step binary communication and do not require a rate code or other spike-based coding scheme, thus producing networks comparable in timing and size to conventional ANNs, albeit with binarized communication. We demonstrate Whetstone on a number of image classification networks, describing how the sharpening process interacts with different training optimizers and changes the distribution of activity within the network. We further note that Whetstone is compatible with several non-classification neural network applications, such as autoencoders and semantic segmentation. Whetstone is widely extendable and currently implemented using custom activation functions within the Keras wrapper to the popular TensorFlow machine learning framework.
Tasks	Image Classification, Semantic Segmentation
Published	2018-10-26
URL	http://arxiv.org/abs/1810.11521v1
PDF	http://arxiv.org/pdf/1810.11521v1.pdf
PWC	https://paperswithcode.com/paper/whetstone-a-method-for-training-deep
Repo
Framework

Hedging Algorithms and Repeated Matrix Games


Title	Hedging Algorithms and Repeated Matrix Games
Authors	Bruno Bouzy, Marc Métivier, Damien Pellier
Abstract	Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that $UCB$, $M3$, $S$ or $Exp3$ algorithms have good behaviours on average in RMG. Besides, hedging algorithms have been shown to be effective on prediction problems. An hedging algorithm is made up with a top-level algorithm and a set of basic algorithms. To make its decision, an hedging algorithm uses its top-level algorithm to choose a basic algorithm, and the chosen algorithm makes the decision. This paper experimentally shows that well-selected hedging algorithms are better on average than all previous MAL algorithms on the task of playing RMG against various players. $S$ is a very good top-level algorithm, and $UCB$ and $M3$ are very good basic algorithms. Furthermore, two-level hedging algorithms are more effective than one-level hedging algorithms, and three levels are not better than two levels.
Tasks
Published	2018-10-15
URL	http://arxiv.org/abs/1810.06443v1
PDF	http://arxiv.org/pdf/1810.06443v1.pdf
PWC	https://paperswithcode.com/paper/hedging-algorithms-and-repeated-matrix-games
Repo
Framework

Boolean Decision Rules via Column Generation


Title	Boolean Decision Rules via Column Generation
Authors	Sanjeeb Dash, Oktay Günlük, Dennis Wei
Abstract	This paper considers the learning of Boolean rules in either disjunctive normal form (DNF, OR-of-ANDs, equivalent to decision rule sets) or conjunctive normal form (CNF, AND-of-ORs) as an interpretable model for classification. An integer program is formulated to optimally trade classification accuracy for rule simplicity. Column generation (CG) is used to efficiently search over an exponential number of candidate clauses (conjunctions or disjunctions) without the need for heuristic rule mining. This approach also bounds the gap between the selected rule set and the best possible rule set on the training data. To handle large datasets, we propose an approximate CG algorithm using randomization. Compared to three recently proposed alternatives, the CG algorithm dominates the accuracy-simplicity trade-off in 7 out of 15 datasets. When maximized for accuracy, CG is competitive with rule learners designed for this purpose, sometimes finding significantly simpler solutions that are no less accurate.
Tasks
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09901v1
PDF	http://arxiv.org/pdf/1805.09901v1.pdf
PWC	https://paperswithcode.com/paper/boolean-decision-rules-via-column-generation
Repo
Framework

Flexible and accurate inference and learning for deep generative models


Title	Flexible and accurate inference and learning for deep generative models
Authors	Eszter Vertes, Maneesh Sahani
Abstract	We introduce a new approach to learning in hierarchical latent-variable generative models called the “distributed distributional code Helmholtz machine”, which emphasises flexibility and accuracy in the inferential process. In common with the original Helmholtz machine and later variational autoencoder algorithms (but unlike adverserial methods) our approach learns an explicit inference or “recognition” model to approximate the posterior distribution over the latent variables. Unlike in these earlier methods, the posterior representation is not limited to a narrow tractable parameterised form (nor is it represented by samples). To train the generative and recognition models we develop an extended wake-sleep algorithm inspired by the original Helmholtz Machine. This makes it possible to learn hierarchical latent models with both discrete and continuous variables, where an accurate posterior representation is essential. We demonstrate that the new algorithm outperforms current state-of-the-art methods on synthetic, natural image patch and the MNIST data sets.
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1805.11051v1
PDF	http://arxiv.org/pdf/1805.11051v1.pdf
PWC	https://paperswithcode.com/paper/flexible-and-accurate-inference-and-learning
Repo
Framework

Weighted Contrastive Divergence


Title	Weighted Contrastive Divergence
Authors	Enrique Romero Merino, Ferran Mazzanti Castrillejo, Jordi Delgado Pin, David Buchaca Prats
Abstract	Learning algorithms for energy based Boltzmann architectures that rely on gradient descent are in general computationally prohibitive, typically due to the exponential number of terms involved in computing the partition function. In this way one has to resort to approximation schemes for the evaluation of the gradient. This is the case of Restricted Boltzmann Machines (RBM) and its learning algorithm Contrastive Divergence (CD). It is well-known that CD has a number of shortcomings, and its approximation to the gradient has several drawbacks. Overcoming these defects has been the basis of much research and new algorithms have been devised, such as persistent CD. In this manuscript we propose a new algorithm that we call Weighted CD (WCD), built from small modifications of the negative phase in standard CD. However small these modifications may be, experimental work reported in this paper suggest that WCD provides a significant improvement over standard CD and persistent CD at a small additional computational cost.
Tasks
Published	2018-01-08
URL	http://arxiv.org/abs/1801.02567v2
PDF	http://arxiv.org/pdf/1801.02567v2.pdf
PWC	https://paperswithcode.com/paper/weighted-contrastive-divergence
Repo
Framework

Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars


Title	Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars
Authors	Ana I. Maqueda, Antonio Loquercio, Guillermo Gallego, Narciso Garcia, Davide Scaramuzza
Abstract	Event cameras are bio-inspired vision sensors that naturally capture the dynamics of a scene, filtering out redundant information. This paper presents a deep neural network approach that unlocks the potential of event cameras on a challenging motion-estimation task: prediction of a vehicle’s steering angle. To make the best out of this sensor-algorithm combination, we adapt state-of-the-art convolutional architectures to the output of event sensors and extensively evaluate the performance of our approach on a publicly available large scale event-camera dataset (~1000 km). We present qualitative and quantitative explanations of why event cameras allow robust steering prediction even in cases where traditional cameras fail, e.g. challenging illumination conditions and fast motion. Finally, we demonstrate the advantages of leveraging transfer learning from traditional to event-based vision, and show that our approach outperforms state-of-the-art algorithms based on standard cameras.
Tasks	Event-based vision, Motion Estimation, Self-Driving Cars, Transfer Learning
Published	2018-04-04
URL	http://arxiv.org/abs/1804.01310v1
PDF	http://arxiv.org/pdf/1804.01310v1.pdf
PWC	https://paperswithcode.com/paper/event-based-vision-meets-deep-learning-on
Repo
Framework