July 27, 2019

2774 words 14 mins read

Paper Group ANR 623

Parallelized Kendall’s Tau Coefficient Computation via SIMD Vectorized Sorting On Many-Integrated-Core Processors. A total uncertainty measure for D numbers based on belief intervals. PSA: A novel optimization algorithm based on survival rules of porcellio scaber. Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Fo …

Parallelized Kendall’s Tau Coefficient Computation via SIMD Vectorized Sorting On Many-Integrated-Core Processors


Title	Parallelized Kendall’s Tau Coefficient Computation via SIMD Vectorized Sorting On Many-Integrated-Core Processors
Authors	Yongchao Liu, Tony Pan, Oded Green, Srinivas Aluru
Abstract	Pairwise association measure is an important operation in data analytics. Kendall’s tau coefficient is one widely used correlation coefficient identifying non-linear relationships between ordinal variables. In this paper, we investigated a parallel algorithm accelerating all-pairs Kendall’s tau coefficient computation via single instruction multiple data (SIMD) vectorized sorting on Intel Xeon Phis by taking advantage of many processing cores and 512-bit SIMD vector instructions. To facilitate workload balancing and overcome on-chip memory limitation, we proposed a generic framework for symmetric all-pairs computation by building provable bijective functions between job identifier and coordinate space. Performance evaluation demonstrated that our algorithm on one 5110P Phi achieves two orders-of-magnitude speedups over 16-threaded MATLAB and three orders-of-magnitude speedups over sequential R, both running on high-end CPUs. Besides, our algorithm exhibited rather good distributed computing scalability with respect to number of Phis. Source code and datasets are publicly available at http://lightpcc.sourceforge.net.
Tasks
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03767v1
PDF	http://arxiv.org/pdf/1704.03767v1.pdf
PWC	https://paperswithcode.com/paper/parallelized-kendalls-tau-coefficient
Repo
Framework

A total uncertainty measure for D numbers based on belief intervals


Title	A total uncertainty measure for D numbers based on belief intervals
Authors	Xinyang Deng, Wen Jiang
Abstract	As a generalization of Dempster-Shafer theory, the theory of D numbers is a new theoretical framework for uncertainty reasoning. Measuring the uncertainty of knowledge or information represented by D numbers is an unsolved issue in that theory. In this paper, inspired by distance based uncertainty measures for Dempster-Shafer theory, a total uncertainty measure for a D number is proposed based on its belief intervals. The proposed total uncertainty measure can simultaneously capture the discord, and non-specificity, and non-exclusiveness involved in D numbers. And some basic properties of this total uncertainty measure, including range, monotonicity, generalized set consistency, are also presented.
Tasks
Published	2017-12-25
URL	http://arxiv.org/abs/1801.00702v1
PDF	http://arxiv.org/pdf/1801.00702v1.pdf
PWC	https://paperswithcode.com/paper/a-total-uncertainty-measure-for-d-numbers
Repo
Framework

PSA: A novel optimization algorithm based on survival rules of porcellio scaber


Title	PSA: A novel optimization algorithm based on survival rules of porcellio scaber
Authors	Yinyan Zhang, Shuai Li
Abstract	Bio-inspired algorithms have received a significant amount of attention in both academic and engineering societies. In this paper, based on the observation of two major survival rules of a species of woodlice, i.e., porcellio scaber, we design and propose an algorithm called the porcellio scaber algorithm (PSA) for solving optimization problems, including differentiable and non-differential ones as well as the case with local optimums. Numerical results based on benchmark problems are presented to validate the efficacy of PSA.
Tasks
Published	2017-09-28
URL	http://arxiv.org/abs/1709.09840v1
PDF	http://arxiv.org/pdf/1709.09840v1.pdf
PWC	https://paperswithcode.com/paper/psa-a-novel-optimization-algorithm-based-on
Repo
Framework

Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection


Title	Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection
Authors	Monit Shah Singh, Vinaychandran Pondenkandath, Bo Zhou, Paul Lukowicz, Marcus Liwicki
Abstract	Convolutional Neural Networks (CNNs) have become the state-of-the-art in various computer vision tasks, but they are still premature for most sensor data, especially in pervasive and wearable computing. A major reason for this is the limited amount of annotated training data. In this paper, we propose the idea of leveraging the discriminative power of pre-trained deep CNNs on 2-dimensional sensor data by transforming the sensor modality to the visual domain. By three proposed strategies, 2D sensor output is converted into pressure distribution imageries. Then we utilize a pre-trained CNN for transfer learning on the converted imagery data. We evaluate our method on a gait dataset of floor surface pressure mapping. We obtain a classification accuracy of 87.66%, which outperforms the conventional machine learning methods by over 10%.
Tasks	Transfer Learning
Published	2017-01-04
URL	http://arxiv.org/abs/1701.01077v3
PDF	http://arxiv.org/pdf/1701.01077v3.pdf
PWC	https://paperswithcode.com/paper/transforming-sensor-data-to-the-image-domain
Repo
Framework

Learners that Use Little Information


Title	Learners that Use Little Information
Authors	Raef Bassily, Shay Moran, Ido Nachum, Jonathan Shafer, Amir Yehudayoff
Abstract	We study learning algorithms that are restricted to using a small amount of information from their input sample. We introduce a category of learning algorithms we term $d$-bit information learners, which are algorithms whose output conveys at most $d$ bits of information of their input. A central theme in this work is that such algorithms generalize. We focus on the learning capacity of these algorithms, and prove sample complexity bounds with tight dependencies on the confidence and error parameters. We also observe connections with well studied notions such as sample compression schemes, Occam’s razor, PAC-Bayes and differential privacy. We discuss an approach that allows us to prove upper bounds on the amount of information that algorithms reveal about their inputs, and also provide a lower bound by showing a simple concept class for which every (possibly randomized) empirical risk minimizer must reveal a lot of information. On the other hand, we show that in the distribution-dependent setting every VC class has empirical risk minimizers that do not reveal a lot of information.
Tasks
Published	2017-10-14
URL	http://arxiv.org/abs/1710.05233v3
PDF	http://arxiv.org/pdf/1710.05233v3.pdf
PWC	https://paperswithcode.com/paper/learners-that-use-little-information
Repo
Framework

Adaptive Classification for Prediction Under a Budget


Title	Adaptive Classification for Prediction Under a Budget
Authors	Feng Nan, Venkatesh Saligrama
Abstract	We propose a novel adaptive approximation approach for test-time resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gating and prediction models on fully labeled training data by means of a bottom-up strategy. Our novel bottom-up method first trains a high-accuracy complex model. Then a low-complexity gating and prediction model are subsequently learned to adaptively approximate the high-accuracy model in regions where low-cost models are capable of making highly accurate predictions. We pose an empirical loss minimization problem with cost constraints to jointly train gating and prediction models. On a number of benchmark datasets our method outperforms state-of-the-art achieving higher accuracy for the same cost.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1705.10194v1
PDF	http://arxiv.org/pdf/1705.10194v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-classification-for-prediction-under
Repo
Framework

Cross-lingual and cross-domain discourse segmentation of entire documents


Title	Cross-lingual and cross-domain discourse segmentation of entire documents
Authors	Chloé Braud, Ophélie Lacroix, Anders Søgaard
Abstract	Discourse segmentation is a crucial step in building end-to-end discourse parsers. However, discourse segmenters only exist for a few languages and domains. Typically they only detect intra-sentential segment boundaries, assuming gold standard sentence and token segmentation, and relying on high-quality syntactic parses and rich heuristics that are not generally available across languages and domains. In this paper, we propose statistical discourse segmenters for five languages and three domains that do not rely on gold pre-annotations. We also consider the problem of learning discourse segmenters when no labeled data is available for a language. Our fully supervised system obtains 89.5% F1 for English newswire, with slight drops in performance on other domains, and we report supervised and unsupervised (cross-lingual) results for five languages in total.
Tasks
Published	2017-04-13
URL	http://arxiv.org/abs/1704.04100v2
PDF	http://arxiv.org/pdf/1704.04100v2.pdf
PWC	https://paperswithcode.com/paper/cross-lingual-and-cross-domain-discourse-1
Repo
Framework

Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection


Title	Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection
Authors	Zizhao Zhang, Fuyong Xing, Hai Su, Xiaoshuang Shi, Lin Yang
Abstract	The fast growing deep learning technologies have become the main solution of many machine learning problems for medical image analysis. Deep convolution neural networks (CNNs), as one of the most important branch of the deep learning family, have been widely investigated for various computer-aided diagnosis tasks including long-term problems and continuously emerging new problems. Image contour detection is a fundamental but challenging task that has been studied for more than four decades. Recently, we have witnessed the significantly improved performance of contour detection thanks to the development of CNNs. Beyond purusing performance in existing natural image benchmarks, contour detection plays a particularly important role in medical image analysis. Segmenting various objects from radiology images or pathology images requires accurate detection of contours. However, some problems, such as discontinuity and shape constraints, are insufficiently studied in CNNs. It is necessary to clarify the challenges to encourage further exploration. The performance of CNN based contour detection relies on the state-of-the-art CNN architectures. Careful investigation of their design principles and motivations is critical and beneficial to contour detection. In this paper, we first review recent development of medical image contour detection and point out the current confronting challenges and problems. We discuss the development of general CNNs and their applications in image contours (or edges) detection. We compare those methods in detail, clarify their strengthens and weaknesses. Then we review their recent applications in medical image analysis and point out limitations, with the goal to light some potential directions in medical image analysis. We expect the paper to cover comprehensive technical ingredients of advanced CNNs to enrich the study in the medical image domain.
Tasks	Contour Detection
Published	2017-08-24
URL	http://arxiv.org/abs/1708.07281v1
PDF	http://arxiv.org/pdf/1708.07281v1.pdf
PWC	https://paperswithcode.com/paper/recent-advances-in-the-applications-of
Repo
Framework

GANGs: Generative Adversarial Network Games


Title	GANGs: Generative Adversarial Network Games
Authors	Frans A. Oliehoek, Rahul Savani, Jose Gallego-Posada, Elise van der Pol, Edwin D. de Jong, Roderich Gross
Abstract	Generative Adversarial Networks (GAN) have become one of the most successful frameworks for unsupervised generative modeling. As GANs are difficult to train much research has focused on this. However, very little of this research has directly exploited game-theoretic techniques. We introduce Generative Adversarial Network Games (GANGs), which explicitly model a finite zero-sum game between a generator ($G$) and classifier ($C$) that use mixed strategies. The size of these games precludes exact solution methods, therefore we define resource-bounded best responses (RBBRs), and a resource-bounded Nash Equilibrium (RB-NE) as a pair of mixed strategies such that neither $G$ or $C$ can find a better RBBR. The RB-NE solution concept is richer than the notion of `local Nash equilibria’ in that it captures not only failures of escaping local optima of gradient descent, but applies to any approximate best response computations, including methods with random restarts. To validate our approach, we solve GANGs with the Parallel Nash Memory algorithm, which provably monotonically converges to an RB-NE. We compare our results to standard GAN setups, and demonstrate that our method deals well with typical GAN problems such as mode collapse, partial mode coverage and forgetting. \|
Tasks
Published	2017-12-02
URL	http://arxiv.org/abs/1712.00679v2
PDF	http://arxiv.org/pdf/1712.00679v2.pdf
PWC	https://paperswithcode.com/paper/gangs-generative-adversarial-network-games
Repo
Framework

Dynamic Steerable Blocks in Deep Residual Networks


Title	Dynamic Steerable Blocks in Deep Residual Networks
Authors	Jörn-Henrik Jacobsen, Bert de Brabandere, Arnold W. M. Smeulders
Abstract	Filters in convolutional networks are typically parameterized in a pixel basis, that does not take prior knowledge about the visual world into account. We investigate the generalized notion of frames designed with image properties in mind, as alternatives to this parametrization. We show that frame-based ResNets and Densenets can improve performance on Cifar-10+ consistently, while having additional pleasant properties like steerability. By exploiting these transformation properties explicitly, we arrive at dynamic steerable blocks. They are an extension of residual blocks, that are able to seamlessly transform filters under pre-defined transformations, conditioned on the input at training and inference time. Dynamic steerable blocks learn the degree of invariance from data and locally adapt filters, allowing them to apply a different geometrical variant of the same filter to each location of the feature map. When evaluated on the Berkeley Segmentation contour detection dataset, our approach outperforms all competing approaches that do not utilize pre-training. Our results highlight the benefits of image-based regularization to deep networks.
Tasks	Contour Detection
Published	2017-06-02
URL	http://arxiv.org/abs/1706.00598v2
PDF	http://arxiv.org/pdf/1706.00598v2.pdf
PWC	https://paperswithcode.com/paper/dynamic-steerable-blocks-in-deep-residual
Repo
Framework

Beyond the Hazard Rate: More Perturbation Algorithms for Adversarial Multi-armed Bandits


Title	Beyond the Hazard Rate: More Perturbation Algorithms for Adversarial Multi-armed Bandits
Authors	Zifan Li, Ambuj Tewari
Abstract	Recent work on follow the perturbed leader (FTPL) algorithms for the adversarial multi-armed bandit problem has highlighted the role of the hazard rate of the distribution generating the perturbations. Assuming that the hazard rate is bounded, it is possible to provide regret analyses for a variety of FTPL algorithms for the multi-armed bandit problem. This paper pushes the inquiry into regret bounds for FTPL algorithms beyond the bounded hazard rate condition. There are good reasons to do so: natural distributions such as the uniform and Gaussian violate the condition. We give regret bounds for both bounded support and unbounded support distributions without assuming the hazard rate condition. We also disprove a conjecture that the Gaussian distribution cannot lead to a low-regret algorithm. In fact, it turns out that it leads to near optimal regret, up to logarithmic factors. A key ingredient in our approach is the introduction of a new notion called the generalized hazard rate.
Tasks	Multi-Armed Bandits
Published	2017-02-17
URL	http://arxiv.org/abs/1702.05536v2
PDF	http://arxiv.org/pdf/1702.05536v2.pdf
PWC	https://paperswithcode.com/paper/beyond-the-hazard-rate-more-perturbation
Repo
Framework

Agree to Disagree: Improving Disagreement Detection with Dual GRUs


Title	Agree to Disagree: Improving Disagreement Detection with Dual GRUs
Authors	Sushant Hiray, Venkatesh Duppada
Abstract	This paper presents models for detecting agreement/disagreement in online discussions. In this work we show that by using a Siamese inspired architecture to encode the discussions, we no longer need to rely on hand-crafted features to exploit the meta thread structure. We evaluate our model on existing online discussion corpora - ABCD, IAC and AWTP. Experimental results on ABCD dataset show that by fusing lexical and word embedding features, our model achieves the state of the art performance of 0.804 average F1 score. We also show that the model trained on ABCD dataset performs competitively on relatively smaller annotated datasets (IAC and AWTP).
Tasks
Published	2017-08-18
URL	http://arxiv.org/abs/1708.05582v1
PDF	http://arxiv.org/pdf/1708.05582v1.pdf
PWC	https://paperswithcode.com/paper/agree-to-disagree-improving-disagreement
Repo
Framework

An Integrated Simulator and Dataset that Combines Grasping and Vision for Deep Learning


Title	An Integrated Simulator and Dataset that Combines Grasping and Vision for Deep Learning
Authors	Matthew Veres, Medhat Moussa, Graham W. Taylor
Abstract	Deep learning is an established framework for learning hierarchical data representations. While compute power is in abundance, one of the main challenges in applying this framework to robotic grasping has been obtaining the amount of data needed to learn these representations, and structuring the data to the task at hand. Among contemporary approaches in the literature, we highlight key properties that have encouraged the use of deep learning techniques, and in this paper, detail our experience in developing a simulator for collecting cylindrical precision grasps of a multi-fingered dexterous robotic hand.
Tasks	Robotic Grasping
Published	2017-02-07
URL	http://arxiv.org/abs/1702.02103v2
PDF	http://arxiv.org/pdf/1702.02103v2.pdf
PWC	https://paperswithcode.com/paper/an-integrated-simulator-and-dataset-that
Repo
Framework

A Reconfigurable Streaming Deep Convolutional Neural Network Accelerator for Internet of Things


Title	A Reconfigurable Streaming Deep Convolutional Neural Network Accelerator for Internet of Things
Authors	Li Du, Yuan Du, Yilei Li, Mau-Chung Frank Chang
Abstract	Convolutional neural network (CNN) offers significant accuracy in image detection. To implement image detection using CNN in the internet of things (IoT) devices, a streaming hardware accelerator is proposed. The proposed accelerator optimizes the energy efficiency by avoiding unnecessary data movement. With unique filter decomposition technique, the accelerator can support arbitrary convolution window size. In addition, max pooling function can be computed in parallel with convolution by using separate pooling unit, thus achieving throughput improvement. A prototype accelerator was implemented in TSMC 65nm technology with a core size of 5mm2. The accelerator can support major CNNs and achieve 152GOPS peak throughput and 434GOPS/W energy efficiency at 350mW, making it a promising hardware accelerator for intelligent IoT devices.
Tasks
Published	2017-07-08
URL	http://arxiv.org/abs/1707.02973v1
PDF	http://arxiv.org/pdf/1707.02973v1.pdf
PWC	https://paperswithcode.com/paper/a-reconfigurable-streaming-deep-convolutional
Repo
Framework

On Kernelized Multi-armed Bandits


Title	On Kernelized Multi-armed Bandits
Authors	Sayak Ray Chowdhury, Aditya Gopalan
Abstract	We consider the stochastic bandit problem with a continuous set of arms, with the expected reward function over the arms assumed to be fixed but unknown. We provide two new Gaussian process-based algorithms for continuous bandit optimization-Improved GP-UCB (IGP-UCB) and GP-Thomson sampling (GP-TS), and derive corresponding regret bounds. Specifically, the bounds hold when the expected reward function belongs to the reproducing kernel Hilbert space (RKHS) that naturally corresponds to a Gaussian process kernel used as input by the algorithms. Along the way, we derive a new self-normalized concentration inequality for vector- valued martingales of arbitrary, possibly infinite, dimension. Finally, experimental evaluation and comparisons to existing algorithms on synthetic and real-world environments are carried out that highlight the favorable gains of the proposed strategies in many cases.
Tasks	Multi-Armed Bandits
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00445v2
PDF	http://arxiv.org/pdf/1704.00445v2.pdf
PWC	https://paperswithcode.com/paper/on-kernelized-multi-armed-bandits
Repo
Framework