October 18, 2019

3127 words 15 mins read

Paper Group ANR 563

Safely Learning to Control the Constrained Linear Quadratic Regulator. Evolutionary Algorithms. Towards resilient machine learning for ransomware detection. Bimodal network architectures for automatic generation of image annotation from text. How to Profile Privacy-Conscious Users in Recommender Systems. Bach2Bach: Generating Music Using A Deep Rei …

Safely Learning to Control the Constrained Linear Quadratic Regulator


Title	Safely Learning to Control the Constrained Linear Quadratic Regulator
Authors	Sarah Dean, Stephen Tu, Nikolai Matni, Benjamin Recht
Abstract	We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques. We present a framework which allows for system identification through persistent excitation, while maintaining safety by guaranteeing the satisfaction of state and input constraints. This framework involves a novel method for synthesizing robust constraint-satisfying feedback controllers, leveraging newly developed tools from system level synthesis. We connect statistical results with cost sub-optimality bounds to give non-asymptotic guarantees on both estimation and controller performance.
Tasks
Published	2018-09-26
URL	https://arxiv.org/abs/1809.10121v2
PDF	https://arxiv.org/pdf/1809.10121v2.pdf
PWC	https://paperswithcode.com/paper/safely-learning-to-control-the-constrained
Repo
Framework

Evolutionary Algorithms


Title	Evolutionary Algorithms
Authors	David W. Corne, Michael A. Lones
Abstract	Evolutionary algorithms (EAs) are population-based metaheuristics, originally inspired by aspects of natural evolution. Modern varieties incorporate a broad mixture of search mechanisms, and tend to blend inspiration from nature with pragmatic engineering concerns; however, all EAs essentially operate by maintaining a population of potential solutions and in some way artificially ‘evolving’ that population over time. Particularly well-known categories of EAs include genetic algorithms (GAs), Genetic Programming (GP), and Evolution Strategies (ES). EAs have proven very successful in practical applications, particularly those requiring solutions to combinatorial problems. EAs are highly flexible and can be configured to address any optimization task, without the requirements for reformulation and/or simplification that would be needed for other techniques. However, this flexibility goes hand in hand with a cost: the tailoring of an EA’s configuration and parameters, so as to provide robust performance for a given class of tasks, is often a complex and time-consuming process. This tailoring process is one of the many ongoing research areas associated with EAs.
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1805.11014v1
PDF	http://arxiv.org/pdf/1805.11014v1.pdf
PWC	https://paperswithcode.com/paper/evolutionary-algorithms
Repo
Framework

Towards resilient machine learning for ransomware detection


Title	Towards resilient machine learning for ransomware detection
Authors	Li Chen, Chih-Yuan Yang, Anindya Paul, Ravi Sahita
Abstract	There has been a surge of interest in using machine learning (ML) to automatically detect malware through their dynamic behaviors. These approaches have achieved significant improvement in detection rates and lower false positive rates at large scale compared with traditional malware analysis methods. ML in threat detection has demonstrated to be a good cop to guard platform security. However it is imperative to evaluate - is ML-powered security resilient enough? In this paper, we juxtapose the resiliency and trustworthiness of ML algorithms for security, via a case study of evaluating the resiliency of ransomware detection via the generative adversarial network (GAN). In this case study, we propose to use GAN to automatically produce dynamic features that exhibit generalized malicious behaviors that can reduce the efficacy of black-box ransomware classifiers. We examine the quality of the GAN-generated samples by comparing the statistical similarity of these samples to real ransomware and benign software. Further we investigate the latent subspace where the GAN-generated samples lie and explore reasons why such samples cause a certain class of ransomware classifiers to degrade in performance. Our focus is to emphasize necessary defense improvement in ML-based approaches for ransomware detection before deployment in the wild. Our results and discoveries should pose relevant questions for defenders such as how ML models can be made more resilient for robust enforcement of security objectives.
Tasks
Published	2018-12-21
URL	https://arxiv.org/abs/1812.09400v2
PDF	https://arxiv.org/pdf/1812.09400v2.pdf
PWC	https://paperswithcode.com/paper/towards-resilient-machine-learning-for
Repo
Framework

Bimodal network architectures for automatic generation of image annotation from text


Title	Bimodal network architectures for automatic generation of image annotation from text
Authors	Mehdi Moradi, Ali Madani, Yaniv Gur, Yufan Guo, Tanveer Syeda-Mahmood
Abstract	Medical image analysis practitioners have embraced big data methodologies. This has created a need for large annotated datasets. The source of big data is typically large image collections and clinical reports recorded for these images. In many cases, however, building algorithms aimed at segmentation and detection of disease requires a training dataset with markings of the areas of interest on the image that match with the described anomalies. This process of annotation is expensive and needs the involvement of clinicians. In this work we propose two separate deep neural network architectures for automatic marking of a region of interest (ROI) on the image best representing a finding location, given a textual report or a set of keywords. One architecture consists of LSTM and CNN components and is trained end to end with images, matching text, and markings of ROIs for those images. The output layer estimates the coordinates of the vertices of a polygonal region. The second architecture uses a network pre-trained on a large dataset of the same image types for learning feature representations of the findings of interest. We show that for a variety of findings from chest X-ray images, both proposed architectures learn to estimate the ROI, as validated by clinical annotations. There is a clear advantage obtained from the architecture with pre-trained imaging network. The centroids of the ROIs marked by this network were on average at a distance equivalent to 5.1% of the image width from the centroids of the ground truth ROIs.
Tasks
Published	2018-09-05
URL	http://arxiv.org/abs/1809.01610v1
PDF	http://arxiv.org/pdf/1809.01610v1.pdf
PWC	https://paperswithcode.com/paper/bimodal-network-architectures-for-automatic
Repo
Framework

How to Profile Privacy-Conscious Users in Recommender Systems


Title	How to Profile Privacy-Conscious Users in Recommender Systems
Authors	Fabrice Benhamouda, Marc Joye
Abstract	Matrix factorization is a popular method to build a recommender system. In such a system, existing users and items are associated to a low-dimension vector called a profile. The profiles of a user and of an item can be combined (via inner product) to predict the rating that the user would get on the item. One important issue of such a system is the so-called cold-start problem: how to allow a user to learn her profile, so that she can then get accurate recommendations? While a profile can be computed if the user is willing to rate well-chosen items and/or provide supplemental attributes or demographics (such as gender), revealing this additional information is known to allow the analyst of the recommender system to infer many more personal sensitive information. We design a protocol to allow privacy-conscious users to benefit from matrix-factorization-based recommender systems while preserving their privacy. More precisely, our protocol enables a user to learn her profile, and from that to predict ratings without the user revealing any personal information. The protocol is secure in the standard model against semi-honest adversaries.
Tasks	Recommendation Systems
Published	2018-12-01
URL	http://arxiv.org/abs/1812.00125v1
PDF	http://arxiv.org/pdf/1812.00125v1.pdf
PWC	https://paperswithcode.com/paper/how-to-profile-privacy-conscious-users-in
Repo
Framework

Bach2Bach: Generating Music Using A Deep Reinforcement Learning Approach


Title	Bach2Bach: Generating Music Using A Deep Reinforcement Learning Approach
Authors	Nikhil Kotecha
Abstract	A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a deep reinforcement learning architecture that predicts and generates polyphonic music aligned with musical rules. The probabilistic model presented is a Bi-axial LSTM trained with a pseudo-kernel reminiscent of a convolutional kernel. To encourage exploration and impose greater global coherence on the generated music, a deep reinforcement learning approach DQN is adopted. When analyzed quantitatively and qualitatively, this approach performs well in composing polyphonic music.
Tasks
Published	2018-12-03
URL	http://arxiv.org/abs/1812.01060v1
PDF	http://arxiv.org/pdf/1812.01060v1.pdf
PWC	https://paperswithcode.com/paper/bach2bach-generating-music-using-a-deep
Repo
Framework

Unsupervised Correlation Analysis


Title	Unsupervised Correlation Analysis
Authors	Yedid Hoshen, Lior Wolf
Abstract	Linking between two data sources is a basic building block in numerous computer vision problems. In this paper, we set to answer a fundamental cognitive question: are prior correspondences necessary for linking between different domains? One of the most popular methods for linking between domains is Canonical Correlation Analysis (CCA). All current CCA algorithms require correspondences between the views. We introduce a new method Unsupervised Correlation Analysis (UCA), which requires no prior correspondences between the two domains. The correlation maximization term in CCA is replaced by a combination of a reconstruction term (similar to autoencoders), full cycle loss, orthogonality and multiple domain confusion terms. Due to lack of supervision, the optimization leads to multiple alternative solutions with similar scores and we therefore introduce a consensus-based mechanism that is often able to recover the desired solution. Remarkably, this suffices in order to link remote domains such as text and images. We also present results on well accepted CCA benchmarks, showing that performance far exceeds other unsupervised baselines, and approaches supervised performance in some cases.
Tasks
Published	2018-04-01
URL	http://arxiv.org/abs/1804.00347v1
PDF	http://arxiv.org/pdf/1804.00347v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-correlation-analysis
Repo
Framework

Cognitive Radar Antenna Selection via Deep Learning


Title	Cognitive Radar Antenna Selection via Deep Learning
Authors	Ahmet M. Elbir, Kumar Vijay Mishra, Yonina C. Eldar
Abstract	Direction of arrival (DoA) estimation of targets improves with the number of elements employed by a phased array radar antenna. Since larger arrays have high associated cost, area and computational load, there is recent interest in thinning the antenna arrays without loss of far-field DoA accuracy. In this context, a cognitive radar may deploy a full array and then select an optimal subarray to transmit and receive the signals in response to changes in the target environment. Prior works have used optimization and greedy search methods to pick the best subarrays cognitively. In this paper, we leverage deep learning to address the antenna selection problem. Specifically, we construct a convolutional neural network (CNN) as a multi-class classification framework where each class designates a different subarray. The proposed network determines a new array every time data is received by the radar, thereby making antenna selection a cognitive operation. Our numerical experiments show that {the proposed CNN structure provides 22% better classification performance than a Support Vector Machine and the resulting subarrays yield 72% more accurate DoA estimates than random array selections.
Tasks
Published	2018-02-27
URL	http://arxiv.org/abs/1802.09736v3
PDF	http://arxiv.org/pdf/1802.09736v3.pdf
PWC	https://paperswithcode.com/paper/cognitive-radar-antenna-selection-via-deep
Repo
Framework

Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning


Title	Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning
Authors	Yichi Zhang, Zhijian Ou
Abstract	An ensemble of neural networks is known to be more robust and accurate than an individual network, however usually with linearly-increased cost in both training and testing. In this work, we propose a two-stage method to learn Sparse Structured Ensembles (SSEs) for neural networks. In the first stage, we run SG-MCMC with group sparse priors to draw an ensemble of samples from the posterior distribution of network parameters. In the second stage, we apply weight-pruning to each sampled network and then perform retraining over the remained connections. In this way of learning SSEs with SG-MCMC and pruning, we not only achieve high prediction accuracy since SG-MCMC enhances exploration of the model-parameter space, but also reduce memory and computation cost significantly in both training and testing of NN ensembles. This is thoroughly evaluated in the experiments of learning SSE ensembles of both FNNs and LSTMs. For example, in LSTM based language modeling (LM), we obtain 21% relative reduction in LM perplexity by learning a SSE of 4 large LSTM models, which has only 30% of model parameters and 70% of computations in total, as compared to the baseline large LSTM LM. To the best of our knowledge, this work represents the first methodology and empirical study of integrating SG-MCMC, group sparse prior and network pruning together for learning NN ensembles.
Tasks	Language Modelling, Network Pruning
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00184v3
PDF	http://arxiv.org/pdf/1803.00184v3.pdf
PWC	https://paperswithcode.com/paper/learning-sparse-structured-ensembles-with-sg
Repo
Framework

Double Neural Counterfactual Regret Minimization


Title	Double Neural Counterfactual Regret Minimization
Authors	Hui Li, Kailiang Hu, Zhibang Ge, Tao Jiang, Yuan Qi, Le Song
Abstract	Counterfactual Regret Minimization (CRF) is a fundamental and effective technique for solving Imperfect Information Games (IIG). However, the original CRF algorithm only works for discrete state and action spaces, and the resulting strategy is maintained as a tabular representation. Such tabular representation limits the method from being directly applied to large games and continuing to improve from a poor strategy profile. In this paper, we propose a double neural representation for the imperfect information games, where one neural network represents the cumulative regret, and the other represents the average strategy. Furthermore, we adopt the counterfactual regret minimization algorithm to optimize this double neural representation. To make neural learning efficient, we also developed several novel techniques including a robust sampling method, mini-batch Monte Carlo Counterfactual Regret Minimization (MCCFR) and Monte Carlo Counterfactual Regret Minimization Plus (MCCFR+) which may be of independent interests. Experimentally, we demonstrate that the proposed double neural algorithm converges significantly better than the reinforcement learning counterpart.
Tasks
Published	2018-12-27
URL	http://arxiv.org/abs/1812.10607v1
PDF	http://arxiv.org/pdf/1812.10607v1.pdf
PWC	https://paperswithcode.com/paper/double-neural-counterfactual-regret
Repo
Framework

A Practitioners’ Guide to Transfer Learning for Text Classification using Convolutional Neural Networks


Title	A Practitioners’ Guide to Transfer Learning for Text Classification using Convolutional Neural Networks
Authors	Tushar Semwal, Gaurav Mathur, Promod Yenigalla, Shivashankar B. Nair
Abstract	Transfer Learning (TL) plays a crucial role when a given dataset has insufficient labeled examples to train an accurate model. In such scenarios, the knowledge accumulated within a model pre-trained on a source dataset can be transferred to a target dataset, resulting in the improvement of the target model. Though TL is found to be successful in the realm of image-based applications, its impact and practical use in Natural Language Processing (NLP) applications is still a subject of research. Due to their hierarchical architecture, Deep Neural Networks (DNN) provide flexibility and customization in adjusting their parameters and depth of layers, thereby forming an apt area for exploiting the use of TL. In this paper, we report the results and conclusions obtained from extensive empirical experiments using a Convolutional Neural Network (CNN) and try to uncover thumb rules to ensure a successful positive transfer. In addition, we also highlight the flawed means that could lead to a negative transfer. We explore the transferability of various layers and describe the effect of varying hyper-parameters on the transfer performance. Also, we present a comparison of accuracy value and model size against state-of-the-art methods. Finally, we derive inferences from the empirical results and provide best practices to achieve a successful positive transfer.
Tasks	Text Classification, Transfer Learning
Published	2018-01-19
URL	http://arxiv.org/abs/1801.06480v1
PDF	http://arxiv.org/pdf/1801.06480v1.pdf
PWC	https://paperswithcode.com/paper/a-practitioners-guide-to-transfer-learning
Repo
Framework

Convergence of the Deep BSDE Method for Coupled FBSDEs


Title	Convergence of the Deep BSDE Method for Coupled FBSDEs
Authors	Jiequn Han, Jihao Long
Abstract	The recently proposed numerical algorithm, deep BSDE method, has shown remarkable performance in solving high-dimensional forward-backward stochastic differential equations (FBSDEs) and parabolic partial differential equations (PDEs). This article lays a theoretical foundation for the deep BSDE method in the general case of coupled FBSDEs. In particular, a posteriori error estimation of the solution is provided and it is proved that the error converges to zero given the universal approximation capability of neural networks. Numerical results are presented to demonstrate the accuracy of the analyzed algorithm in solving high-dimensional coupled FBSDEs.
Tasks
Published	2018-11-03
URL	https://arxiv.org/abs/1811.01165v3
PDF	https://arxiv.org/pdf/1811.01165v3.pdf
PWC	https://paperswithcode.com/paper/convergence-of-the-deep-bsde-method-for
Repo
Framework

Multi-objective Contextual Bandit Problem with Similarity Information


Title	Multi-objective Contextual Bandit Problem with Similarity Information
Authors	Eralp Turğay, Doruk Öner, Cem Tekin
Abstract	In this paper we propose the multi-objective contextual bandit problem with similarity information. This problem extends the classical contextual bandit problem with similarity information by introducing multiple and possibly conflicting objectives. Since the best arm in each objective can be different given the context, learning the best arm based on a single objective can jeopardize the rewards obtained from the other objectives. In order to evaluate the performance of the learner in this setup, we use a performance metric called the contextual Pareto regret. Essentially, the contextual Pareto regret is the sum of the distances of the arms chosen by the learner to the context dependent Pareto front. For this problem, we develop a new online learning algorithm called Pareto Contextual Zooming (PCZ), which exploits the idea of contextual zooming to learn the arms that are close to the Pareto front for each observed context by adaptively partitioning the joint context-arm set according to the observed rewards and locations of the context-arm pairs selected in the past. Then, we prove that PCZ achieves $\tilde O (T^{(1+d_p)/(2+d_p)})$ Pareto regret where $d_p$ is the Pareto zooming dimension that depends on the size of the set of near-optimal context-arm pairs. Moreover, we show that this regret bound is nearly optimal by providing an almost matching $\Omega (T^{(1+d_p)/(2+d_p)})$ lower bound.
Tasks
Published	2018-03-11
URL	http://arxiv.org/abs/1803.04015v1
PDF	http://arxiv.org/pdf/1803.04015v1.pdf
PWC	https://paperswithcode.com/paper/multi-objective-contextual-bandit-problem
Repo
Framework

Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD


Title	Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD
Authors	Sanghamitra Dutta, Gauri Joshi, Soumyadip Ghosh, Parijat Dube, Priya Nagpurkar
Abstract	Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in waiting for the slowest learners (stragglers). Asynchronous methods can alleviate stragglers, but cause gradient staleness that can adversely affect convergence. In this work we present a novel theoretical characterization of the speed-up offered by asynchronous methods by analyzing the trade-off between the error in the trained model and the actual training runtime (wallclock time). The novelty in our work is that our runtime analysis considers random straggler delays, which helps us design and compare distributed SGD algorithms that strike a balance between stragglers and staleness. We also present a new convergence analysis of asynchronous SGD variants without bounded or exponential delay assumptions, and a novel learning rate schedule to compensate for gradient staleness.
Tasks
Published	2018-03-03
URL	http://arxiv.org/abs/1803.01113v3
PDF	http://arxiv.org/pdf/1803.01113v3.pdf
PWC	https://paperswithcode.com/paper/slow-and-stale-gradients-can-win-the-race
Repo
Framework

Inverting Supervised Representations with Autoregressive Neural Density Models


Title	Inverting Supervised Representations with Autoregressive Neural Density Models
Authors	Charlie Nash, Nate Kushman, Christopher K. I. Williams
Abstract	We present a method for feature interpretation that makes use of recent advances in autoregressive density estimation models to invert model representations. We train generative inversion models to express a distribution over input features conditioned on intermediate model representations. Insights into the invariances learned by supervised models can be gained by viewing samples from these inversion models. In addition, we can use these inversion models to estimate the mutual information between a model’s inputs and its intermediate representations, thus quantifying the amount of information preserved by the network at different stages. Using this method we examine the types of information preserved at different layers of convolutional neural networks, and explore the invariances induced by different architectural choices. Finally we show that the mutual information between inputs and network layers decreases over the course of training, supporting recent work by Shwartz-Ziv and Tishby (2017) on the information bottleneck theory of deep learning.
Tasks	Density Estimation
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00400v2
PDF	http://arxiv.org/pdf/1806.00400v2.pdf
PWC	https://paperswithcode.com/paper/inverting-supervised-representations-with
Repo
Framework