Paper Group ANR 696
Online Adaptive Methods, Universality and Acceleration. Gradient Similarity: An Explainable Approach to Detect Adversarial Attacks against Deep Learning. Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. Deep Reinforcement Learning for Intelligent Transportation Systems. Automated bird sound recognition in re …
Online Adaptive Methods, Universality and Acceleration
Title | Online Adaptive Methods, Universality and Acceleration |
Authors | Kfir Y. Levy, Alp Yurtsever, Volkan Cevher |
Abstract | We present a novel method for convex unconstrained optimization that, without any modifications, ensures: (i) accelerated convergence rate for smooth objectives, (ii) standard convergence rate in the general (non-smooth) setting, and (iii) standard convergence rate in the stochastic optimization setting. To the best of our knowledge, this is the first method that simultaneously applies to all of the above settings. At the heart of our method is an adaptive learning rate rule that employs importance weights, in the spirit of adaptive online learning algorithms (Duchi et al., 2011; Levy, 2017), combined with an update that linearly couples two sequences, in the spirit of (Allen-Zhu and Orecchia, 2017). An empirical examination of our method demonstrates its applicability to the above mentioned scenarios and corroborates our theoretical findings. |
Tasks | Stochastic Optimization |
Published | 2018-09-08 |
URL | http://arxiv.org/abs/1809.02864v1 |
http://arxiv.org/pdf/1809.02864v1.pdf | |
PWC | https://paperswithcode.com/paper/online-adaptive-methods-universality-and |
Repo | |
Framework | |
Gradient Similarity: An Explainable Approach to Detect Adversarial Attacks against Deep Learning
Title | Gradient Similarity: An Explainable Approach to Detect Adversarial Attacks against Deep Learning |
Authors | Jasjeet Dhaliwal, Saurabh Shintre |
Abstract | Deep neural networks are susceptible to small-but-specific adversarial perturbations capable of deceiving the network. This vulnerability can lead to potentially harmful consequences in security-critical applications. To address this vulnerability, we propose a novel metric called \emph{Gradient Similarity} that allows us to capture the influence of training data on test inputs. We show that \emph{Gradient Similarity} behaves differently for normal and adversarial inputs, and enables us to detect a variety of adversarial attacks with a near perfect ROC-AUC of 95-100%. Even white-box adversaries equipped with perfect knowledge of the system cannot bypass our detector easily. On the MNIST dataset, white-box attacks are either detected with a high ROC-AUC of 87-96%, or require very high distortion to bypass our detector. |
Tasks | |
Published | 2018-06-27 |
URL | http://arxiv.org/abs/1806.10707v1 |
http://arxiv.org/pdf/1806.10707v1.pdf | |
PWC | https://paperswithcode.com/paper/gradient-similarity-an-explainable-approach |
Repo | |
Framework | |
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
Title | Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems |
Authors | Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright |
Abstract | We study derivative-free methods for policy optimization over the class of linear policies. We focus on characterizing the convergence rate of these methods when applied to linear-quadratic systems, and study various settings of driving noise and reward feedback. We show that these methods provably converge to within any pre-specified tolerance of the optimal policy with a number of zero-order evaluations that is an explicit polynomial of the error tolerance, dimension, and curvature properties of the problem. Our analysis reveals some interesting differences between the settings of additive driving noise and random initialization, as well as the settings of one-point and two-point reward feedback. Our theory is corroborated by extensive simulations of derivative-free methods on these systems. Along the way, we derive convergence rates for stochastic zero-order optimization algorithms when applied to a certain class of non-convex problems. |
Tasks | |
Published | 2018-12-20 |
URL | http://arxiv.org/abs/1812.08305v2 |
http://arxiv.org/pdf/1812.08305v2.pdf | |
PWC | https://paperswithcode.com/paper/derivative-free-methods-for-policy |
Repo | |
Framework | |
Deep Reinforcement Learning for Intelligent Transportation Systems
Title | Deep Reinforcement Learning for Intelligent Transportation Systems |
Authors | Xiao-Yang Liu, Zihan Ding, Sem Borst, Anwar Walid |
Abstract | Intelligent Transportation Systems (ITSs) are envisioned to play a critical role in improving traffic flow and reducing congestion, which is a pervasive issue impacting urban areas around the globe. Rapidly advancing vehicular communication and edge cloud computation technologies provide key enablers for smart traffic management. However, operating viable real-time actuation mechanisms on a practically relevant scale involves formidable challenges, e.g., policy iteration and conventional Reinforcement Learning (RL) techniques suffer from poor scalability due to state space explosion. Motivated by these issues, we explore the potential for Deep Q-Networks (DQN) to optimize traffic light control policies. As an initial benchmark, we establish that the DQN algorithms yield the “thresholding” policy in a single-intersection. Next, we examine the scalability properties of DQN algorithms and their performance in a linear network topology with several intersections along a main artery. We demonstrate that DQN algorithms produce intelligent behavior, such as the emergence of “greenwave” patterns, reflecting their ability to learn favorable traffic light actuations. |
Tasks | |
Published | 2018-12-03 |
URL | http://arxiv.org/abs/1812.00979v1 |
http://arxiv.org/pdf/1812.00979v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-intelligent |
Repo | |
Framework | |
Automated bird sound recognition in realistic settings
Title | Automated bird sound recognition in realistic settings |
Authors | Timos Papadopoulos, Stephen J. Roberts, Katherine J. Willis |
Abstract | We evaluated the effectiveness of an automated bird sound identification system in a situation that emulates a realistic, typical application. We trained classification algorithms on a crowd-sourced collection of bird audio recording data and restricted our training methods to be completely free of manual intervention. The approach is hence directly applicable to the analysis of multiple species collections, with labelling provided by crowd-sourced collection. We evaluated the performance of the bird sound recognition system on a realistic number of candidate classes, corresponding to real conditions. We investigated the use of two canonical classification methods, chosen due to their widespread use and ease of interpretation, namely a k Nearest Neighbour (kNN) classifier with histogram-based features and a Support Vector Machine (SVM) with time-summarisation features. We further investigated the use of a certainty measure, derived from the output probabilities of the classifiers, to enhance the interpretability and reliability of the class decisions. Our results demonstrate that both identification methods achieved similar performance, but we argue that the use of the kNN classifier offers somewhat more flexibility. Furthermore, we show that employing an outcome certainty measure provides a valuable and consistent indicator of the reliability of classification results. Our use of generic training data and our investigation of probabilistic classification methodologies that can flexibly address the variable number of candidate species/classes that are expected to be encountered in the field, directly contribute to the development of a practical bird sound identification system with potentially global application. Further, we show that certainty measures associated with identification outcomes can significantly contribute to the practical usability of the overall system. |
Tasks | |
Published | 2018-09-04 |
URL | http://arxiv.org/abs/1809.01133v1 |
http://arxiv.org/pdf/1809.01133v1.pdf | |
PWC | https://paperswithcode.com/paper/automated-bird-sound-recognition-in-realistic |
Repo | |
Framework | |
Exploiting Document Knowledge for Aspect-level Sentiment Classification
Title | Exploiting Document Knowledge for Aspect-level Sentiment Classification |
Authors | Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier |
Abstract | Attention-based long short-term memory (LSTM) networks have proven to be useful in aspect-level sentiment classification. However, due to the difficulties in annotating aspect-level data, existing public datasets for this task are all relatively small, which largely limits the effectiveness of those neural models. In this paper, we explore two approaches that transfer knowledge from document- level data, which is much less expensive to obtain, to improve the performance of aspect-level sentiment classification. We demonstrate the effectiveness of our approaches on 4 public datasets from SemEval 2014, 2015, and 2016, and we show that attention-based LSTM benefits from document-level knowledge in multiple ways. |
Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
Published | 2018-06-12 |
URL | http://arxiv.org/abs/1806.04346v1 |
http://arxiv.org/pdf/1806.04346v1.pdf | |
PWC | https://paperswithcode.com/paper/exploiting-document-knowledge-for-aspect |
Repo | |
Framework | |
Explaining the Ambiguity of Object Detection and 6D Pose From Visual Data
Title | Explaining the Ambiguity of Object Detection and 6D Pose From Visual Data |
Authors | Fabian Manhardt, Diego Martin Arroyo, Christian Rupprecht, Benjamin Busam, Tolga Birdal, Nassir Navab, Federico Tombari |
Abstract | 3D object detection and pose estimation from a single image are two inherently ambiguous problems. Oftentimes, objects appear similar from different viewpoints due to shape symmetries, occlusion and repetitive textures. This ambiguity in both detection and pose estimation means that an object instance can be perfectly described by several different poses and even classes. In this work we propose to explicitly deal with this uncertainty. For each object instance we predict multiple pose and class outcomes to estimate the specific pose distribution generated by symmetries and repetitive textures. The distribution collapses to a single outcome when the visual appearance uniquely identifies just one valid pose. We show the benefits of our approach which provides not only a better explanation for pose ambiguity, but also a higher accuracy in terms of pose estimation. |
Tasks | 3D Object Detection, Object Detection, Pose Estimation |
Published | 2018-12-01 |
URL | https://arxiv.org/abs/1812.00287v2 |
https://arxiv.org/pdf/1812.00287v2.pdf | |
PWC | https://paperswithcode.com/paper/explaining-the-ambiguity-of-object-detection |
Repo | |
Framework | |
VBALD - Variational Bayesian Approximation of Log Determinants
Title | VBALD - Variational Bayesian Approximation of Log Determinants |
Authors | Diego Granziol, Edward Wagstaff, Bin Xin Ru, Michael Osborne, Stephen Roberts |
Abstract | Evaluating the log determinant of a positive definite matrix is ubiquitous in machine learning. Applications thereof range from Gaussian processes, minimum-volume ellipsoids, metric learning, kernel learning, Bayesian neural networks, Determinental Point Processes, Markov random fields to partition functions of discrete graphical models. In order to avoid the canonical, yet prohibitive, Cholesky $\mathcal{O}(n^{3})$ computational cost, we propose a novel approach, with complexity $\mathcal{O}(n^{2})$, based on a constrained variational Bayes algorithm. We compare our method to Taylor, Chebyshev and Lanczos approaches and show state of the art performance on both synthetic and real-world datasets. |
Tasks | Gaussian Processes, Metric Learning, Point Processes |
Published | 2018-02-21 |
URL | http://arxiv.org/abs/1802.08054v1 |
http://arxiv.org/pdf/1802.08054v1.pdf | |
PWC | https://paperswithcode.com/paper/vbald-variational-bayesian-approximation-of |
Repo | |
Framework | |
Optical Flow Based Online Moving Foreground Analysis
Title | Optical Flow Based Online Moving Foreground Analysis |
Authors | Junjie Huang, Wei Zou, Zheng Zhu, Jiagang Zhu |
Abstract | Obtained by moving object detection, the foreground mask result is unshaped and can not be directly used in most subsequent processes. In this paper, we focus on this problem and address it by constructing an optical flow based moving foreground analysis framework. During the processing procedure, the foreground masks are analyzed and segmented through two complementary clustering algorithms. As a result, we obtain the instance-level information like the number, location and size of moving objects. The experimental result show that our method adapts itself to the problem and performs well enough for practical applications. |
Tasks | Object Detection, Optical Flow Estimation |
Published | 2018-11-18 |
URL | http://arxiv.org/abs/1811.07256v1 |
http://arxiv.org/pdf/1811.07256v1.pdf | |
PWC | https://paperswithcode.com/paper/optical-flow-based-online-moving-foreground |
Repo | |
Framework | |
The Power of The Hybrid Model for Mean Estimation
Title | The Power of The Hybrid Model for Mean Estimation |
Authors | Yatharth Dubey, Aleksandra Korolova |
Abstract | In this work we explore the power of the hybrid model of differential privacy (DP) proposed by Avent et al., where some users desire the guarantees of the local model of DP and others are content with receiving the trusted curator model guarantees. In particular, we study the accuracy of mean estimation algorithms for arbitrary distributions in bounded support. We show that a hybrid mechanism which combines the sample mean estimates obtained from the two groups in an optimally weighted convex combination performs a constant factor better for a wide range of sample sizes than natural benchmarks. We analyze how this improvement factor is parameterized by the problem setting and how it varies with sample size. |
Tasks | |
Published | 2018-11-29 |
URL | http://arxiv.org/abs/1811.12040v1 |
http://arxiv.org/pdf/1811.12040v1.pdf | |
PWC | https://paperswithcode.com/paper/the-power-of-the-hybrid-model-for-mean |
Repo | |
Framework | |
Toward Marker-free 3D Pose Estimation in Lifting: A Deep Multi-view Solution
Title | Toward Marker-free 3D Pose Estimation in Lifting: A Deep Multi-view Solution |
Authors | Rahil Mehrizi, Xi Peng, Zhiqiang Tang, Xu Xu, Dimitris Metaxas, Kang Li |
Abstract | Lifting is a common manual material handling task performed in the workplaces. It is considered as one of the main risk factors for Work-related Musculoskeletal Disorders. To improve work place safety, it is necessary to assess musculoskeletal and biomechanical risk exposures associated with these tasks, which requires very accurate 3D pose. Existing approaches mainly utilize marker-based sensors to collect 3D information. However, these methods are usually expensive to setup, time-consuming in process, and sensitive to the surrounding environment. In this study, we propose a multi-view based deep perceptron approach to address aforementioned limitations. Our approach consists of two modules: a “view-specific perceptron” network extracts rich information independently from the image of view, which includes both 2D shape and hierarchical texture information; while a “multi-view integration” network synthesizes information from all available views to predict accurate 3D pose. To fully evaluate our approach, we carried out comprehensive experiments to compare different variants of our design. The results prove that our approach achieves comparable performance with former marker-based methods, i.e. an average error of $14.72 \pm 2.96$ mm on the lifting dataset. The results are also compared with state-of-the-art methods on HumanEva-I dataset, which demonstrates the superior performance of our approach. |
Tasks | 3D Pose Estimation, Pose Estimation |
Published | 2018-02-06 |
URL | http://arxiv.org/abs/1802.01741v1 |
http://arxiv.org/pdf/1802.01741v1.pdf | |
PWC | https://paperswithcode.com/paper/toward-marker-free-3d-pose-estimation-in |
Repo | |
Framework | |
Generating Multilingual Parallel Corpus Using Subtitles
Title | Generating Multilingual Parallel Corpus Using Subtitles |
Authors | Farshad Jafari |
Abstract | Neural Machine Translation with its significant results, still has a great problem: lack or absence of parallel corpus for many languages. This article suggests a method for generating considerable amount of parallel corpus for any language pairs, extracted from open source materials existing on the Internet. Parallel corpus contents will be derived from video subtitles. It needs a set of video titles, with some attributes like release date, rating, duration and etc. Process of finding and downloading subtitle pairs for desired language pairs is automated by using a crawler. Finally sentence pairs will be extracted from synchronous dialogues in subtitles. The main problem of this method is unsynchronized subtitle pairs. Therefore subtitles will be verified before downloading. If two subtitle were not synchronized, then another subtitle of that video will be processed till it finds the matching subtitle. Using this approach gives ability to make context based parallel corpus through filtering videos by genre. Context based corpus can be used in complex translators which decode sentences by different networks after determining contents subject. Languages have many differences in their formal and informal styles, including words and syntax. Other advantage of this method is to make corpus of informal style of languages. Because most of movies dialogues are parts of a conversation. So they had informal style. This feature of generated corpus can be used in real-time translators to have more accurate conversation translations. |
Tasks | Machine Translation |
Published | 2018-04-11 |
URL | http://arxiv.org/abs/1804.03923v1 |
http://arxiv.org/pdf/1804.03923v1.pdf | |
PWC | https://paperswithcode.com/paper/generating-multilingual-parallel-corpus-using |
Repo | |
Framework | |
Endowing Robots with Longer-term Autonomy by Recovering from External Disturbances in Manipulation through Grounded Anomaly Classification and Recovery Policies
Title | Endowing Robots with Longer-term Autonomy by Recovering from External Disturbances in Manipulation through Grounded Anomaly Classification and Recovery Policies |
Authors | Hongmin Wu, Shuangqi Luo, Longxin Chen, Shuangda Duan, Sakmongkon Chumkamon, Dong Liu, Yisheng Guan, Juan Rojas |
Abstract | Robot manipulation is increasingly poised to interact with humans in co-shared workspaces. Despite increasingly robust manipulation and control algorithms, failure modes continue to exist whenever models do not capture the dynamics of the unstructured environment. To obtain longer-term horizons in robot automation, robots must develop introspection and recovery abilities. We contribute a set of recovery policies to deal with anomalies produced by external disturbances as well as anomaly classification through the use of non-parametric statistics with memoized variational inference with scalable adaptation. A recovery critic stands atop of a tightly-integrated, graph-based online motion-generation and introspection system that resolves a wide range of anomalous situations. Policies, skills, and introspection models are learned incrementally and contextually in a task. Two task-level recovery policies: re-enactment and adaptation resolve accidental and persistent anomalies respectively. The introspection system uses non-parametric priors along with Markov jump linear systems and memoized variational inference with scalable adaptation to learn a model from the data. Extensive real-robot experimentation with various strenuous anomalous conditions is induced and resolved at different phases of a task and in different combinations. The system executes around-the-clock introspection and recovery and even elicited self-recovery when misclassifications occurred. |
Tasks | |
Published | 2018-09-11 |
URL | http://arxiv.org/abs/1809.03979v1 |
http://arxiv.org/pdf/1809.03979v1.pdf | |
PWC | https://paperswithcode.com/paper/endowing-robots-with-longer-term-autonomy-by |
Repo | |
Framework | |
A Scheme-Driven Approach to Learning Programs from Input/Output Equations
Title | A Scheme-Driven Approach to Learning Programs from Input/Output Equations |
Authors | Jochen Burghardt |
Abstract | We describe an approach to learn, in a term-rewriting setting, function definitions from input/output equations. By confining ourselves to structurally recursive definitions we obtain a fairly fast learning algorithm that often yields definitions close to intuitive expectations. We provide a Prolog prototype implementation of our approach, and indicate open issues of further investigation. |
Tasks | |
Published | 2018-02-04 |
URL | http://arxiv.org/abs/1802.01177v1 |
http://arxiv.org/pdf/1802.01177v1.pdf | |
PWC | https://paperswithcode.com/paper/a-scheme-driven-approach-to-learning-programs |
Repo | |
Framework | |
Optimality and Sub-optimality of PCA I: Spiked Random Matrix Models
Title | Optimality and Sub-optimality of PCA I: Spiked Random Matrix Models |
Authors | Amelia Perry, Alexander S. Wein, Afonso S. Bandeira, Ankur Moitra |
Abstract | A central problem of random matrix theory is to understand the eigenvalues of spiked random matrix models, introduced by Johnstone, in which a prominent eigenvector (or “spike”) is planted into a random matrix. These distributions form natural statistical models for principal component analysis (PCA) problems throughout the sciences. Baik, Ben Arous and Peche showed that the spiked Wishart ensemble exhibits a sharp phase transition asymptotically: when the spike strength is above a critical threshold, it is possible to detect the presence of a spike based on the top eigenvalue, and below the threshold the top eigenvalue provides no information. Such results form the basis of our understanding of when PCA can detect a low-rank signal in the presence of noise. However, under structural assumptions on the spike, not all information is necessarily contained in the spectrum. We study the statistical limits of tests for the presence of a spike, including non-spectral tests. Our results leverage Le Cam’s notion of contiguity, and include: i) For the Gaussian Wigner ensemble, we show that PCA achieves the optimal detection threshold for certain natural priors for the spike. ii) For any non-Gaussian Wigner ensemble, PCA is sub-optimal for detection. However, an efficient variant of PCA achieves the optimal threshold (for natural priors) by pre-transforming the matrix entries. iii) For the Gaussian Wishart ensemble, the PCA threshold is optimal for positive spikes (for natural priors) but this is not always the case for negative spikes. |
Tasks | |
Published | 2018-07-02 |
URL | http://arxiv.org/abs/1807.00891v2 |
http://arxiv.org/pdf/1807.00891v2.pdf | |
PWC | https://paperswithcode.com/paper/optimality-and-sub-optimality-of-pca-i-spiked |
Repo | |
Framework | |