July 26, 2019

2951 words 14 mins read

Paper Group ANR 760

A Comparison of Reinforcement Learning Techniques for Fuzzy Cloud Auto-Scaling. Towards Proving the Adversarial Robustness of Deep Neural Networks. Combining Representation Learning with Logic for Language Processing. Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters. An ELU Network with Total Variation f …

A Comparison of Reinforcement Learning Techniques for Fuzzy Cloud Auto-Scaling


Title	A Comparison of Reinforcement Learning Techniques for Fuzzy Cloud Auto-Scaling
Authors	Hamid Arabnejad, Claus Pahl, Pooyan Jamshidi, Giovani Estrada
Abstract	A goal of cloud service management is to design self-adaptable auto-scaler to react to workload fluctuations and changing the resources assigned. The key problem is how and when to add/remove resources in order to meet agreed service-level agreements. Reducing application cost and guaranteeing service-level agreements (SLAs) are two critical factors of dynamic controller design. In this paper, we compare two dynamic learning strategies based on a fuzzy logic system, which learns and modifies fuzzy scaling rules at runtime. A self-adaptive fuzzy logic controller is combined with two reinforcement learning (RL) approaches: (i) Fuzzy SARSA learning (FSL) and (ii) Fuzzy Q-learning (FQL). As an off-policy approach, Q-learning learns independent of the policy currently followed, whereas SARSA as an on-policy always incorporates the actual agent’s behavior and leads to faster learning. Both approaches are implemented and compared in their advantages and disadvantages, here in the OpenStack cloud platform. We demonstrate that both auto-scaling approaches can handle various load traffic situations, sudden and periodic, and delivering resources on demand while reducing operating costs and preventing SLA violations. The experimental results demonstrate that FSL and FQL have acceptable performance in terms of adjusted number of virtual machine targeted to optimize SLA compliance and response time.
Tasks	Q-Learning
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07114v1
PDF	http://arxiv.org/pdf/1705.07114v1.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-reinforcement-learning
Repo
Framework

Towards Proving the Adversarial Robustness of Deep Neural Networks


Title	Towards Proving the Adversarial Robustness of Deep Neural Networks
Authors	Guy Katz, Clark Barrett, David L. Dill, Kyle Julian, Mykel J. Kochenderfer
Abstract	Autonomous vehicles are highly complex systems, required to function reliably in a wide variety of situations. Manually crafting software controllers for these vehicles is difficult, but there has been some success in using deep neural networks generated using machine-learning. However, deep neural networks are opaque to human engineers, rendering their correctness very difficult to prove manually; and existing automated techniques, which were not designed to operate on neural networks, fail to scale to large systems. This paper focuses on proving the adversarial robustness of deep neural networks, i.e. proving that small perturbations to a correctly-classified input to the network cannot cause it to be misclassified. We describe some of our recent and ongoing work on verifying the adversarial robustness of networks, and discuss some of the open questions we have encountered and how they might be addressed.
Tasks	Autonomous Vehicles
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02802v1
PDF	http://arxiv.org/pdf/1709.02802v1.pdf
PWC	https://paperswithcode.com/paper/towards-proving-the-adversarial-robustness-of
Repo
Framework

Combining Representation Learning with Logic for Language Processing


Title	Combining Representation Learning with Logic for Language Processing
Authors	Tim Rocktäschel
Abstract	The current state-of-the-art in many natural language processing and automated knowledge base completion tasks is held by representation learning methods which learn distributed vector representations of symbols via gradient-based optimization. They require little or no hand-crafted features, thus avoiding the need for most preprocessing steps and task-specific assumptions. However, in many cases representation learning requires a large amount of annotated training data to generalize well to unseen data. Such labeled training data is provided by human annotators who often use formal logic as the language for specifying annotations. This thesis investigates different combinations of representation learning methods with logic for reducing the need for annotated training data, and for improving generalization.
Tasks	Knowledge Base Completion, Representation Learning
Published	2017-12-27
URL	http://arxiv.org/abs/1712.09687v1
PDF	http://arxiv.org/pdf/1712.09687v1.pdf
PWC	https://paperswithcode.com/paper/combining-representation-learning-with-logic
Repo
Framework

Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters


Title	Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters
Authors	Luke de Oliveira, Michela Paganini, Benjamin Nachman
Abstract	High-precision modeling of subatomic particle interactions is critical for many fields within the physical sciences, such as nuclear physics and high energy particle physics. Most simulation pipelines in the sciences are computationally intensive – in a variety of scientific fields, Generative Adversarial Networks have been suggested as a solution to speed up the forward component of simulation, with promising results. An important component of any simulation system for the sciences is the ability to condition on any number of physically meaningful latent characteristics that can effect the forward generation procedure. We introduce an auxiliary task to the training of a Generative Adversarial Network on particle showers in a multi-layer electromagnetic calorimeter, which allows our model to learn an attribute-aware conditioning mechanism.
Tasks
Published	2017-11-23
URL	http://arxiv.org/abs/1711.08813v1
PDF	http://arxiv.org/pdf/1711.08813v1.pdf
PWC	https://paperswithcode.com/paper/controlling-physical-attributes-in-gan
Repo
Framework

An ELU Network with Total Variation for Image Denoising


Title	An ELU Network with Total Variation for Image Denoising
Authors	Tianyang Wang, Zhengrui Qin, Michelle Zhu
Abstract	In this paper, we propose a novel convolutional neural network (CNN) for image denoising, which uses exponential linear unit (ELU) as the activation function. We investigate the suitability by analyzing ELU’s connection with trainable nonlinear reaction diffusion model (TNRD) and residual denoising. On the other hand, batch normalization (BN) is indispensable for residual denoising and convergence purpose. However, direct stacking of BN and ELU degrades the performance of CNN. To mitigate this issue, we design an innovative combination of activation layer and normalization layer to exploit and leverage the ELU network, and discuss the corresponding rationale. Moreover, inspired by the fact that minimizing total variation (TV) can be applied to image denoising, we propose a TV regularized L2 loss to evaluate the training effect during the iterations. Finally, we conduct extensive experiments, showing that our model outperforms some recent and popular approaches on Gaussian denoising with specific or randomized noise levels for both gray and color images.
Tasks	Denoising, Image Denoising
Published	2017-08-14
URL	http://arxiv.org/abs/1708.04317v1
PDF	http://arxiv.org/pdf/1708.04317v1.pdf
PWC	https://paperswithcode.com/paper/an-elu-network-with-total-variation-for-image
Repo
Framework

End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks


Title	End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks
Authors	Szu-Wei Fu, Tao-Wei Wang, Yu Tsao, Xugang Lu, Hisashi Kawai
Abstract	Speech enhancement model is used to map a noisy speech to a clean speech. In the training stage, an objective function is often adopted to optimize the model parameters. However, in most studies, there is an inconsistency between the model optimization criterion and the evaluation criterion on the enhanced speech. For example, in measuring speech intelligibility, most of the evaluation metric is based on a short-time objective intelligibility (STOI) measure, while the frame based minimum mean square error (MMSE) between estimated and clean speech is widely used in optimizing the model. Due to the inconsistency, there is no guarantee that the trained model can provide optimal performance in applications. In this study, we propose an end-to-end utterance-based speech enhancement framework using fully convolutional neural networks (FCN) to reduce the gap between the model optimization and evaluation criterion. Because of the utterance-based optimization, temporal correlation information of long speech segments, or even at the entire utterance level, can be considered when perception-based objective functions are used for the direct optimization. As an example, we implement the proposed FCN enhancement framework to optimize the STOI measure. Experimental results show that the STOI of test speech is better than conventional MMSE-optimized speech due to the consistency between the training and evaluation target. Moreover, by integrating the STOI in model optimization, the intelligibility of human subjects and automatic speech recognition (ASR) system on the enhanced speech is also substantially improved compared to those generated by the MMSE criterion.
Tasks	Speech Enhancement, Speech Recognition
Published	2017-09-12
URL	http://arxiv.org/abs/1709.03658v2
PDF	http://arxiv.org/pdf/1709.03658v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-waveform-utterance-enhancement-for
Repo
Framework

Comparative Performance Analysis of Neural Networks Architectures on H2O Platform for Various Activation Functions


Title	Comparative Performance Analysis of Neural Networks Architectures on H2O Platform for Various Activation Functions
Authors	Yuriy Kochura, Sergii Stirenko, Yuri Gordienko
Abstract	Deep learning (deep structured learning, hierarchi- cal learning or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high- level abstractions in data by using multiple processing layers with complex structures or otherwise composed of multiple non-linear transformations. In this paper, we present the results of testing neural networks architectures on H2O platform for various activation functions, stopping metrics, and other parameters of machine learning algorithm. It was demonstrated for the use case of MNIST database of handwritten digits in single-threaded mode that blind selection of these parameters can hugely increase (by 2-3 orders) the runtime without the significant increase of precision. This result can have crucial influence for opitmization of available and new machine learning methods, especially for image recognition problems.
Tasks
Published	2017-07-16
URL	http://arxiv.org/abs/1707.04940v1
PDF	http://arxiv.org/pdf/1707.04940v1.pdf
PWC	https://paperswithcode.com/paper/comparative-performance-analysis-of-neural
Repo
Framework

Online Learning with Automata-based Expert Sequences


Title	Online Learning with Automata-based Expert Sequences
Authors	Mehryar Mohri, Scott Yang
Abstract	We consider a general framework of online learning with expert advice where regret is defined with respect to sequences of experts accepted by a weighted automaton. Our framework covers several problems previously studied, including competing against k-shifting experts. We give a series of algorithms for this problem, including an automata-based algorithm extending weighted-majority and more efficient algorithms based on the notion of failure transitions. We further present efficient algorithms based on an approximation of the competitor automaton, in particular n-gram models obtained by minimizing the \infty-R'{e}nyi divergence, and present an extensive study of the approximation properties of such models. Finally, we also extend our algorithms and results to the framework of sleeping experts.
Tasks
Published	2017-04-29
URL	http://arxiv.org/abs/1705.00132v4
PDF	http://arxiv.org/pdf/1705.00132v4.pdf
PWC	https://paperswithcode.com/paper/online-learning-with-automata-based-expert
Repo
Framework

A generic and fast C++ optimization framework


Title	A generic and fast C++ optimization framework
Authors	Ryan R. Curtin, Shikhar Bhardwaj, Marcus Edel, Yannis Mentekidis
Abstract	The development of the mlpack C++ machine learning library (http://www.mlpack.org/) has required the design and implementation of a flexible, robust optimization system that is able to solve the types of arbitrary optimization problems that may arise all throughout machine learning problems. In this paper, we present the generic optimization framework that we have designed for mlpack. A key priority in the design was ease of implementation of both new optimizers and new objective functions to be optimized; therefore, implementation of a new optimizer requires only one method and implementation of a new objective function requires at most four functions. This leads to simple and intuitive code, which, for fast prototyping and experimentation, is of paramount importance. When compared to optimization frameworks of other libraries, we find that mlpack’s supports more types of objective functions, is able to make optimizations that other frameworks do not, and seamlessly supports user-defined objective functions and optimizers.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06581v1
PDF	http://arxiv.org/pdf/1711.06581v1.pdf
PWC	https://paperswithcode.com/paper/a-generic-and-fast-c-optimization-framework
Repo
Framework

Lightweight Neural Networks


Title	Lightweight Neural Networks
Authors	Altaf H. Khan
Abstract	Most of the weights in a Lightweight Neural Network have a value of zero, while the remaining ones are either +1 or -1. These universal approximators require approximately 1.1 bits/weight of storage, posses a quick forward pass and achieve classification accuracies similar to conventional continuous-weight networks. Their training regimen focuses on error reduction initially, but later emphasizes discretization of weights. They ignore insignificant inputs, remove unnecessary weights, and drop unneeded hidden neurons. We have successfully tested them on the MNIST, credit card fraud, and credit card defaults data sets using networks having 2 to 16 hidden layers and up to 4.4 million weights.
Tasks
Published	2017-12-15
URL	http://arxiv.org/abs/1712.05695v1
PDF	http://arxiv.org/pdf/1712.05695v1.pdf
PWC	https://paperswithcode.com/paper/lightweight-neural-networks
Repo
Framework

Adaptive Threshold Sampling and Estimation


Title	Adaptive Threshold Sampling and Estimation
Authors	Daniel Ting
Abstract	Sampling is a fundamental problem in both computer science and statistics. A number of issues arise when designing a method based on sampling. These include statistical considerations such as constructing a good sampling design and ensuring there are good, tractable estimators for the quantities of interest as well as computational considerations such as designing fast algorithms for streaming data and ensuring the sample fits within memory constraints. Unfortunately, existing sampling methods are only able to address all of these issues in limited scenarios. We develop a framework that can be used to address these issues in a broad range of scenarios. In particular, it addresses the problem of drawing and using samples under some memory budget constraint. This problem can be challenging since the memory budget forces samples to be drawn non-independently and consequently, makes computation of resulting estimators difficult. At the core of the framework is the notion of a data adaptive thresholding scheme where the threshold effectively allows one to treat the non-independent sample as if it were drawn independently. We provide sufficient conditions for a thresholding scheme to allow this and provide ways to build and compose such schemes. Furthermore, we provide fast algorithms to efficiently sample under these thresholding schemes.
Tasks
Published	2017-08-16
URL	http://arxiv.org/abs/1708.04970v1
PDF	http://arxiv.org/pdf/1708.04970v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-threshold-sampling-and-estimation
Repo
Framework

LV-ROVER: Lexicon Verified Recognizer Output Voting Error Reduction


Title	LV-ROVER: Lexicon Verified Recognizer Output Voting Error Reduction
Authors	Bruno Stuner, Clément Chatelain, Thierry Paquet
Abstract	Offline handwritten text line recognition is a hard task that requires both an efficient optical character recognizer and language model. Handwriting recognition state of the art methods are based on Long Short Term Memory (LSTM) recurrent neural networks (RNN) coupled with the use of linguistic knowledge. Most of the proposed approaches in the literature focus on improving one of the two components and use constraint, dedicated to a database lexicon. However, state of the art performance is achieved by combining multiple optical models, and possibly multiple language models with the Recognizer Output Voting Error Reduction (ROVER) framework. Though handwritten line recognition with ROVER has been implemented by combining only few recognizers because training multiple complete recognizers is hard. In this paper we propose a Lexicon Verified ROVER: LV-ROVER, that has a reduce complexity compare to the original one and that can combine hundreds of recognizers without language models. We achieve state of the art for handwritten line text on the RIMES dataset.
Tasks	Language Modelling
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07432v1
PDF	http://arxiv.org/pdf/1707.07432v1.pdf
PWC	https://paperswithcode.com/paper/lv-rover-lexicon-verified-recognizer-output
Repo
Framework

A Brief Survey of Deep Reinforcement Learning


Title	A Brief Survey of Deep Reinforcement Learning
Authors	Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, Anil Anthony Bharath
Abstract	Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to play video games directly from pixels. Deep reinforcement learning algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of reinforcement learning, then progress to the main streams of value-based and policy-based methods. Our survey will cover central algorithms in deep reinforcement learning, including the deep $Q$-network, trust region policy optimisation, and asynchronous advantage actor-critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via reinforcement learning. To conclude, we describe several current areas of research within the field.
Tasks
Published	2017-08-19
URL	http://arxiv.org/abs/1708.05866v2
PDF	http://arxiv.org/pdf/1708.05866v2.pdf
PWC	https://paperswithcode.com/paper/a-brief-survey-of-deep-reinforcement-learning
Repo
Framework

Contrastive Learning for Image Captioning


Title	Contrastive Learning for Image Captioning
Authors	Bo Dai, Dahua Lin
Abstract	Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of captions, as distinctive captions are more likely to describe images with their unique aspects. In this work, we propose a new learning method, Contrastive Learning (CL), for image captioning. Specifically, via two constraints formulated on top of a reference model, the proposed method can encourage distinctiveness, while maintaining the overall quality of the generated captions. We tested our method on two challenging datasets, where it improves the baseline model by significant margins. We also showed in our studies that the proposed method is generic and can be used for models with various structures.
Tasks	Image Captioning
Published	2017-10-06
URL	http://arxiv.org/abs/1710.02534v1
PDF	http://arxiv.org/pdf/1710.02534v1.pdf
PWC	https://paperswithcode.com/paper/contrastive-learning-for-image-captioning
Repo
Framework

Sequential Matrix Completion


Title	Sequential Matrix Completion
Authors	Annie Marsden, Sergio Bacallado
Abstract	We propose a novel algorithm for sequential matrix completion in a recommender system setting, where the $(i,j)$th entry of the matrix corresponds to a user $i$'s rating of product $j$. The objective of the algorithm is to provide a sequential policy for user-product pair recommendation which will yield the highest possible ratings after a finite time horizon. The algorithm uses a Gamma process factor model with two posterior-focused bandit policies, Thompson Sampling and Information-Directed Sampling. While Thompson Sampling shows competitive performance in simulations, state-of-the-art performance is obtained from Information-Directed Sampling, which makes its recommendations based off a ratio between the expected reward and a measure of information gain. To our knowledge, this is the first implementation of Information Directed Sampling on large real datasets. This approach contributes to a recent line of research on bandit approaches to collaborative filtering including Kawale et al. (2015), Li et al. (2010), Bresler et al. (2014), Li et al. (2016), Deshpande & Montanari (2012), and Zhao et al. (2013). The setting of this paper, as has been noted in Kawale et al. (2015) and Zhao et al. (2013), presents significant challenges to bounding regret after finite horizons. We discuss these challenges in relation to simpler models for bandits with side information, such as linear or gaussian process bandits, and hope the experiments presented here motivate further research toward theoretical guarantees.
Tasks	Matrix Completion, Recommendation Systems
Published	2017-10-23
URL	http://arxiv.org/abs/1710.08045v1
PDF	http://arxiv.org/pdf/1710.08045v1.pdf
PWC	https://paperswithcode.com/paper/sequential-matrix-completion
Repo
Framework