July 27, 2019

3123 words 15 mins read

Paper Group ANR 630

Representation of big data by dimension reduction. Deep Learning in a Generalized HJM-type Framework Through Arbitrage-Free Regularization. Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusing. Learning with Privileged Information for Multi-Label Classification. Communication-efficient Algorithms for Dis …

Representation of big data by dimension reduction


Title	Representation of big data by dimension reduction
Authors	A. G. Ramm, C. Van
Abstract	Suppose the data consist of a set $S$ of points $x_j, 1 \leq j \leq J$, distributed in a bounded domain $D \subset R^N$, where $N$ and $J$ are large numbers. In this paper an algorithm is proposed for checking whether there exists a manifold $\mathbb{M}$ of low dimension near which many of the points of $S$ lie and finding such $\mathbb{M}$ if it exists. There are many dimension reduction algorithms, both linear and non-linear. Our algorithm is simple to implement and has some advantages compared with the known algorithms. If there is a manifold of low dimension near which most of the data points lie, the proposed algorithm will find it. Some numerical results are presented illustrating the algorithm and analyzing its performance compared to the classical PCA (principal component analysis) and Isomap.
Tasks	Dimensionality Reduction
Published	2017-01-31
URL	http://arxiv.org/abs/1702.00027v1
PDF	http://arxiv.org/pdf/1702.00027v1.pdf
PWC	https://paperswithcode.com/paper/representation-of-big-data-by-dimension
Repo
Framework

Deep Learning in a Generalized HJM-type Framework Through Arbitrage-Free Regularization


Title	Deep Learning in a Generalized HJM-type Framework Through Arbitrage-Free Regularization
Authors	Anastasis Kratsios, Cody B. Hyndman
Abstract	We introduce a regularization approach to arbitrage-free factor-model selection. The considered model selection problem seeks to learn the closest arbitrage-free HJM-type model to any prespecified factor-model. An asymptotic solution to this, a priori computationally intractable, problem is represented as the limit of a 1-parameter family of optimizers to computationally tractable model selection tasks. Each of these simplified model-selection tasks seeks to learn the most similar model, to the prescribed factor-model, subject to a penalty detecting when the reference measure is a local martingale-measure for the entire underlying financial market. A simple expression for the penalty terms is obtained in the bond market withing the affine-term structure setting, and it is used to formulate a deep-learning approach to arbitrage-free affine term-structure modelling. Numerical implementations are also performed to evaluate the performance in the bond market.
Tasks	Model Selection
Published	2017-10-14
URL	https://arxiv.org/abs/1710.05114v4
PDF	https://arxiv.org/pdf/1710.05114v4.pdf
PWC	https://paperswithcode.com/paper/arbitrage-free-regularization
Repo
Framework

Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusing


Title	Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusing
Authors	Wei Li, Farnaz Abitahi, Zhigang Zhu
Abstract	Action Unit (AU) detection becomes essential for facial analysis. Many proposed approaches face challenging problems in dealing with the alignments of different face regions, in the effective fusion of temporal information, and in training a model for multiple AU labels. To better address these problems, we propose a deep learning framework for AU detection with region of interest (ROI) adaptation, integrated multi-label learning, and optimal LSTM-based temporal fusing. First, ROI cropping nets (ROI Nets) are designed to make sure specifically interested regions of faces are learned independently; each sub-region has a local convolutional neural network (CNN) - an ROI Net, whose convolutional filters will only be trained for the corresponding region. Second, multi-label learning is employed to integrate the outputs of those individual ROI cropping nets, which learns the inter-relationships of various AUs and acquires global features across sub-regions for AU detection. Finally, the optimal selection of multiple LSTM layers to form the best LSTM Net is carried out to best fuse temporal features, in order to make the AU prediction the most accurate. The proposed approach is evaluated on two popular AU detection datasets, BP4D and DISFA, outperforming the state of the art significantly, with an average improvement of around 13% on BP4D and 25% on DISFA, respectively.
Tasks	Action Unit Detection, Multi-Label Learning
Published	2017-04-10
URL	http://arxiv.org/abs/1704.03067v1
PDF	http://arxiv.org/pdf/1704.03067v1.pdf
PWC	https://paperswithcode.com/paper/action-unit-detection-with-region-adaptation
Repo
Framework

Learning with Privileged Information for Multi-Label Classification


Title	Learning with Privileged Information for Multi-Label Classification
Authors	Shiyu Chen, Shangfei Wang, Tanfang Chen, Xiaoxiao Shi
Abstract	In this paper, we propose a novel approach for learning multi-label classifiers with the help of privileged information. Specifically, we use similarity constraints to capture the relationship between available information and privileged information, and use ranking constraints to capture the dependencies among multiple labels. By integrating similarity constraints and ranking constraints into the learning process of classifiers, the privileged information and the dependencies among multiple labels are exploited to construct better classifiers during training. A maximum margin classifier is adopted, and an efficient learning algorithm of the proposed method is also developed. We evaluate the proposed method on two applications: multiple object recognition from images with the help of implicit information about object importance conveyed by the list of manually annotated image tags; and multiple facial action unit detection from low-resolution images augmented by high-resolution images. Experimental results demonstrate that the proposed method can effectively take full advantage of privileged information and dependencies among multiple labels for better object recognition and better facial action unit detection.
Tasks	Action Unit Detection, Facial Action Unit Detection, Multi-Label Classification, Object Recognition
Published	2017-03-29
URL	http://arxiv.org/abs/1703.09911v1
PDF	http://arxiv.org/pdf/1703.09911v1.pdf
PWC	https://paperswithcode.com/paper/learning-with-privileged-information-for
Repo
Framework

Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis


Title	Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis
Authors	Dan Garber, Ohad Shamir, Nathan Srebro
Abstract	We study the fundamental problem of Principal Component Analysis in a statistical distributed setting in which each machine out of $m$ stores a sample of $n$ points sampled i.i.d. from a single unknown distribution. We study algorithms for estimating the leading principal component of the population covariance matrix that are both communication-efficient and achieve estimation error of the order of the centralized ERM solution that uses all $mn$ samples. On the negative side, we show that in contrast to results obtained for distributed estimation under convexity assumptions, for the PCA objective, simply averaging the local ERM solutions cannot guarantee error that is consistent with the centralized ERM. We show that this unfortunate phenomena can be remedied by performing a simple correction step which correlates between the individual solutions, and provides an estimator that is consistent with the centralized ERM for sufficiently-large $n$. We also introduce an iterative distributed algorithm that is applicable in any regime of $n$, which is based on distributed matrix-vector products. The algorithm gives significant acceleration in terms of communication rounds over previous distributed algorithms, in a wide regime of parameters.
Tasks
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08169v1
PDF	http://arxiv.org/pdf/1702.08169v1.pdf
PWC	https://paperswithcode.com/paper/communication-efficient-algorithms-for
Repo
Framework

Reasoning about Fine-grained Attribute Phrases using Reference Games


Title	Reasoning about Fine-grained Attribute Phrases using Reference Games
Authors	Jong-Chyi Su, Chenyun Wu, Huaizu Jiang, Subhransu Maji
Abstract	We present a framework for learning to describe fine-grained visual differences between instances using attribute phrases. Attribute phrases capture distinguishing aspects of an object (e.g., “propeller on the nose” or “door near the wing” for airplanes) in a compositional manner. Instances within a category can be described by a set of these phrases and collectively they span the space of semantic attributes for a category. We collect a large dataset of such phrases by asking annotators to describe several visual differences between a pair of instances within a category. We then learn to describe and ground these phrases to images in the context of a reference game between a speaker and a listener. The goal of a speaker is to describe attributes of an image that allows the listener to correctly identify it within a pair. Data collected in a pairwise manner improves the ability of the speaker to generate, and the ability of the listener to interpret visual descriptions. Moreover, due to the compositionality of attribute phrases, the trained listeners can interpret descriptions not seen during training for image retrieval, and the speakers can generate attribute-based explanations for differences between previously unseen categories. We also show that embedding an image into the semantic space of attribute phrases derived from listeners offers 20% improvement in accuracy over existing attribute-based representations on the FGVC-aircraft dataset.
Tasks	Image Retrieval
Published	2017-08-29
URL	http://arxiv.org/abs/1708.08874v1
PDF	http://arxiv.org/pdf/1708.08874v1.pdf
PWC	https://paperswithcode.com/paper/reasoning-about-fine-grained-attribute
Repo
Framework

Regularization and feature selection for large dimensional data


Title	Regularization and feature selection for large dimensional data
Authors	Nand Sharma, Prathamesh Verlekar, Rehab Ashary, Sui Zhiquan
Abstract	Feature selection has evolved to be an important step in several machine learning paradigms. In domains like bio-informatics and text classification which involve data of high dimensions, feature selection can help in drastically reducing the feature space. In cases where it is difficult or infeasible to obtain sufficient number of training examples, feature selection helps overcome the curse of dimensionality which in turn helps improve performance of the classification algorithm. The focus of our research here are five embedded feature selection methods which use either the ridge regression, or Lasso regression, or a combination of the two in the regularization part of the optimization function. We evaluate five chosen methods on five large dimensional datasets and compare them on the parameters of sparsity and correlation in the datasets and their execution times.
Tasks	Feature Selection, Text Classification
Published	2017-12-06
URL	http://arxiv.org/abs/1712.01975v3
PDF	http://arxiv.org/pdf/1712.01975v3.pdf
PWC	https://paperswithcode.com/paper/sparsity-regularization-and-feature-selection
Repo
Framework

Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets


Title	Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets
Authors	Denis Steckelmacher, Diederik M. Roijers, Anna Harutyunyan, Peter Vrancx, Hélène Plisnier, Ann Nowé
Abstract	Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are usually tackled separately (for instance by combining recurrent neural networks and options), we show that addressing both problems simultaneously is simpler and more efficient in many cases. More specifically, we make the initiation set of options conditional on the previously-executed option, and show that options with such Option-Observation Initiation Sets (OOIs) are at least as expressive as Finite State Controllers (FSCs), a state-of-the-art approach for learning in POMDPs. OOIs are easy to design based on an intuitive description of the task, lead to explainable policies and keep the top-level and option policies memoryless. Our experiments show that OOIs allow agents to learn optimal policies in challenging POMDPs, while being much more sample-efficient than a recurrent neural network over options.
Tasks
Published	2017-08-22
URL	http://arxiv.org/abs/1708.06551v2
PDF	http://arxiv.org/pdf/1708.06551v2.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-in-pomdps-with
Repo
Framework

Progression of Decomposed Local-Effect Action Theories


Title	Progression of Decomposed Local-Effect Action Theories
Authors	Denis Ponomaryov, Mikhail Soutchanski
Abstract	In many tasks related to reasoning about consequences of a logical theory, it is desirable to decompose the theory into a number of weakly-related or independent components. However, a theory may represent knowledge that is subject to change, as a result of executing actions that have effects on some of the initial properties mentioned in the theory. Having once computed a decomposition of a theory, it is advantageous to know whether a decomposition has to be computed again in the newly-changed theory (obtained from taking into account changes resulting from execution of an action). In the paper, we address this problem in the scope of the situation calculus, where a change of an initial theory is related to the notion of progression. Progression provides a form of forward reasoning; it relies on forgetting values of those properties, which are subject to change, and computing new values for them. We consider decomposability and inseparability, two component properties known from the literature, and contribute by 1) studying the conditions when these properties are preserved and 2) when they are lost wrt progression and the related operation of forgetting. To show the latter, we demonstrate the boundaries using a number of negative examples. To show the former, we identify cases when these properties are preserved under forgetting and progression of initial theories in local-effect basic action theories of the situation calculus. Our paper contributes to bridging two different communities in Knowledge Representation, namely research on modularity and research on reasoning about actions.
Tasks
Published	2017-05-12
URL	http://arxiv.org/abs/1705.04712v1
PDF	http://arxiv.org/pdf/1705.04712v1.pdf
PWC	https://paperswithcode.com/paper/progression-of-decomposed-local-effect-action
Repo
Framework

Runaway Feedback Loops in Predictive Policing


Title	Runaway Feedback Loops in Predictive Policing
Authors	Danielle Ensign, Sorelle A. Friedler, Scott Neville, Carlos Scheidegger, Suresh Venkatasubramanian
Abstract	Predictive policing systems are increasingly used to determine how to allocate police across a city in order to best prevent crime. Discovered crime data (e.g., arrest counts) are used to help update the model, and the process is repeated. Such systems have been empirically shown to be susceptible to runaway feedback loops, where police are repeatedly sent back to the same neighborhoods regardless of the true crime rate. In response, we develop a mathematical model of predictive policing that proves why this feedback loop occurs, show empirically that this model exhibits such problems, and demonstrate how to change the inputs to a predictive policing system (in a black-box manner) so the runaway feedback loop does not occur, allowing the true crime rate to be learned. Our results are quantitative: we can establish a link (in our model) between the degree to which runaway feedback causes problems and the disparity in crime rates between areas. Moreover, we can also demonstrate the way in which \emph{reported} incidents of crime (those reported by residents) and \emph{discovered} incidents of crime (i.e. those directly observed by police officers dispatched as a result of the predictive policing algorithm) interact: in brief, while reported incidents can attenuate the degree of runaway feedback, they cannot entirely remove it without the interventions we suggest.
Tasks
Published	2017-06-29
URL	http://arxiv.org/abs/1706.09847v3
PDF	http://arxiv.org/pdf/1706.09847v3.pdf
PWC	https://paperswithcode.com/paper/runaway-feedback-loops-in-predictive-policing
Repo
Framework

Deep Generative Adversarial Compression Artifact Removal


Title	Deep Generative Adversarial Compression Artifact Removal
Authors	Leonardo Galteri, Lorenzo Seidenari, Marco Bertini, Alberto Del Bimbo
Abstract	Compression artifacts arise in images whenever a lossy compression algorithm is applied. These artifacts eliminate details present in the original image, or add noise and small structures; because of these effects they make images less pleasant for the human eye, and may also lead to decreased performance of computer vision algorithms such as object detectors. To eliminate such artifacts, when decompressing an image, it is required to recover the original image from a disturbed version. To this end, we present a feed-forward fully convolutional residual network model trained using a generative adversarial framework. To provide a baseline, we show that our model can be also trained optimizing the Structural Similarity (SSIM), which is a better loss with respect to the simpler Mean Squared Error (MSE). Our GAN is able to produce images with more photorealistic details than MSE or SSIM based networks. Moreover we show that our approach can be used as a pre-processing step for object detection in case images are degraded by compression to a point that state-of-the art detectors fail. In this task, our GAN method obtains better performance than MSE or SSIM trained networks.
Tasks	Object Detection
Published	2017-04-08
URL	http://arxiv.org/abs/1704.02518v3
PDF	http://arxiv.org/pdf/1704.02518v3.pdf
PWC	https://paperswithcode.com/paper/deep-generative-adversarial-compression
Repo
Framework

The Mean and Median Criterion for Automatic Kernel Bandwidth Selection for Support Vector Data Description


Title	The Mean and Median Criterion for Automatic Kernel Bandwidth Selection for Support Vector Data Description
Authors	Arin Chaudhuri, Deovrat Kakde, Carol Sadek, Laura Gonzalez, Seunghyun Kong
Abstract	Support vector data description (SVDD) is a popular technique for detecting anomalies. The SVDD classifier partitions the whole space into an inlier region, which consists of the region near the training data, and an outlier region, which consists of points away from the training data. The computation of the SVDD classifier requires a kernel function, and the Gaussian kernel is a common choice for the kernel function. The Gaussian kernel has a bandwidth parameter, whose value is important for good results. A small bandwidth leads to overfitting, and the resulting SVDD classifier overestimates the number of anomalies. A large bandwidth leads to underfitting, and the classifier fails to detect many anomalies. In this paper we present a new automatic, unsupervised method for selecting the Gaussian kernel bandwidth. The selected value can be computed quickly, and it is competitive with existing bandwidth selection methods.
Tasks
Published	2017-08-16
URL	http://arxiv.org/abs/1708.05106v2
PDF	http://arxiv.org/pdf/1708.05106v2.pdf
PWC	https://paperswithcode.com/paper/the-mean-and-median-criterion-for-automatic
Repo
Framework

Accelerated Stochastic Quasi-Newton Optimization on Riemann Manifolds


Title	Accelerated Stochastic Quasi-Newton Optimization on Riemann Manifolds
Authors	Anirban Roychowdhury
Abstract	We propose an L-BFGS optimization algorithm on Riemannian manifolds using minibatched stochastic variance reduction techniques for fast convergence with constant step sizes, without resorting to linesearch methods designed to satisfy Wolfe conditions. We provide a new convergence proof for strongly convex functions without using curvature conditions on the manifold, as well as a convergence discussion for nonconvex functions. We discuss a couple of ways to obtain the correction pairs used to calculate the product of the gradient with the inverse Hessian, and empirically demonstrate their use in synthetic experiments on computation of Karcher means for symmetric positive definite matrices and leading eigenvalues of large scale data matrices. We compare our method to VR-PCA for the latter experiment, along with Riemannian SVRG for both cases, and show strong convergence results for a range of datasets.
Tasks
Published	2017-04-06
URL	http://arxiv.org/abs/1704.01700v3
PDF	http://arxiv.org/pdf/1704.01700v3.pdf
PWC	https://paperswithcode.com/paper/accelerated-stochastic-quasi-newton
Repo
Framework

A Study of FOSS’2013 Survey Data Using Clustering Techniques


Title	A Study of FOSS’2013 Survey Data Using Clustering Techniques
Authors	Mani A, Rebeka Mukherjee
Abstract	FOSS is an acronym for Free and Open Source Software. The FOSS 2013 survey primarily targets FOSS contributors and relevant anonymized dataset is publicly available under CC by SA license. In this study, the dataset is analyzed from a critical perspective using statistical and clustering techniques (especially multiple correspondence analysis) with a strong focus on women contributors towards discovering hidden trends and facts. Important inferences are drawn about development practices and other facets of the free software and OSS worlds.
Tasks
Published	2017-01-28
URL	http://arxiv.org/abs/1701.08302v2
PDF	http://arxiv.org/pdf/1701.08302v2.pdf
PWC	https://paperswithcode.com/paper/a-study-of-foss2013-survey-data-using
Repo
Framework

Isotropic and Steerable Wavelets in N Dimensions. A multiresolution analysis framework for ITK


Title	Isotropic and Steerable Wavelets in N Dimensions. A multiresolution analysis framework for ITK
Authors	Pablo Hernandez-Cerdan
Abstract	This document describes the implementation of the external module ITKIsotropicWavelets, a multiresolution (MRA) analysis framework using isotropic and steerable wavelets in the frequency domain. This framework provides the backbone for state of the art filters for denoising, feature detection or phase analysis in N-dimensions. It focus on reusability, and highly decoupled modules for easy extension and implementation of new filters, and it contains a filter for multiresolution phase analysis, The backbone of the multi-scale analysis is provided by an isotropic band-limited wavelet pyramid, and the detection of directional features is provided by coupling the pyramid with a generalized Riesz transform. The generalized Riesz transform of order N behaves like a smoothed version of the Nth order derivatives of the signal. Also, it is steerable: its components impulse responses can be rotated to any spatial orientation, reducing computation time when detecting directional features.
Tasks	Denoising
Published	2017-10-03
URL	http://arxiv.org/abs/1710.01103v1
PDF	http://arxiv.org/pdf/1710.01103v1.pdf
PWC	https://paperswithcode.com/paper/isotropic-and-steerable-wavelets-in-n
Repo
Framework