May 7, 2019

2919 words 14 mins read

Paper Group ANR 92

Team-Optimal Distributed MMSE Estimation in General and Tree Networks. Best-of-K Bandits. Robust Matrix Regression. Safe Probability. PSDVec: a Toolbox for Incremental and Scalable Word Embedding. The Evolutionary Process of Image Transition in Conjunction with Box and Strip Mutation. Interactive Tools and Tasks for the Hebrew Bible. Complex Decomp …

Team-Optimal Distributed MMSE Estimation in General and Tree Networks


Title	Team-Optimal Distributed MMSE Estimation in General and Tree Networks
Authors	Muhammed O. Sayin, Suleyman S. Kozat, Tamer Başar
Abstract	We construct team-optimal estimation algorithms over distributed networks for state estimation in the finite-horizon mean-square error (MSE) sense. Here, we have a distributed collection of agents with processing and cooperation capabilities. These agents observe noisy samples of a desired state through a linear model and seek to learn this state by interacting with each other. Although this problem has attracted significant attention and been studied extensively in fields including machine learning and signal processing, all the well-known strategies do not achieve team-optimal learning performance in the finite-horizon MSE sense. To this end, we formulate the finite-horizon distributed minimum MSE (MMSE) when there is no restriction on the size of the disclosed information, i.e., oracle performance, over an arbitrary network topology. Subsequently, we show that exchange of local estimates is sufficient to achieve the oracle performance only over certain network topologies. By inspecting these network structures, we propose recursive algorithms achieving the oracle performance through the disclosure of local estimates. For practical implementations we also provide approaches to reduce the complexity of the algorithms through the time-windowing of the observations. Finally, in the numerical examples, we demonstrate the superior performance of the introduced algorithms in the finite-horizon MSE sense due to optimal estimation.
Tasks
Published	2016-10-03
URL	http://arxiv.org/abs/1610.00681v2
PDF	http://arxiv.org/pdf/1610.00681v2.pdf
PWC	https://paperswithcode.com/paper/team-optimal-distributed-mmse-estimation-in
Repo
Framework

Best-of-K Bandits


Title	Best-of-K Bandits
Authors	Max Simchowitz, Kevin Jamieson, Benjamin Recht
Abstract	This paper studies the Best-of-K Bandit game: At each time the player chooses a subset S among all N-choose-K possible options and observes reward max(X(i) : i in S) where X is a random vector drawn from a joint distribution. The objective is to identify the subset that achieves the highest expected reward with high probability using as few queries as possible. We present distribution-dependent lower bounds based on a particular construction which force a learner to consider all N-choose-K subsets, and match naive extensions of known upper bounds in the bandit setting obtained by treating each subset as a separate arm. Nevertheless, we present evidence that exhaustive search may be avoided for certain, favorable distributions because the influence of high-order order correlations may be dominated by lower order statistics. Finally, we present an algorithm and analysis for independent arms, which mitigates the surprising non-trivial information occlusion that occurs due to only observing the max in the subset. This may inform strategies for more general dependent measures, and we complement these result with independent-arm lower bounds.
Tasks
Published	2016-03-09
URL	http://arxiv.org/abs/1603.02752v2
PDF	http://arxiv.org/pdf/1603.02752v2.pdf
PWC	https://paperswithcode.com/paper/best-of-k-bandits
Repo
Framework

Robust Matrix Regression


Title	Robust Matrix Regression
Authors	Hang Zhang, Fengyuan Zhu, Shixin Li
Abstract	Modern technologies are producing datasets with complex intrinsic structures, and they can be naturally represented as matrices instead of vectors. To preserve the latent data structures during processing, modern regression approaches incorporate the low-rank property to the model and achieve satisfactory performance for certain applications. These approaches all assume that both predictors and labels for each pair of data within the training set are accurate. However, in real-world applications, it is common to see the training data contaminated by noises, which can affect the robustness of these matrix regression methods. In this paper, we address this issue by introducing a novel robust matrix regression method. We also derive efficient proximal algorithms for model training. To evaluate the performance of our methods, we apply it to real world applications with comparative studies. Our method achieves the state-of-the-art performance, which shows the effectiveness and the practical value of our method.
Tasks
Published	2016-11-15
URL	http://arxiv.org/abs/1611.04686v1
PDF	http://arxiv.org/pdf/1611.04686v1.pdf
PWC	https://paperswithcode.com/paper/robust-matrix-regression
Repo
Framework

Safe Probability


Title	Safe Probability
Authors	Peter Grünwald
Abstract	We formalize the idea of probability distributions that lead to reliable predictions about some, but not all aspects of a domain. The resulting notion of `safety’ provides a fresh perspective on foundational issues in statistics, providing a middle ground between imprecise probability and multiple-prior models on the one hand and strictly Bayesian approaches on the other. It also allows us to formalize fiducial distributions in terms of the set of random variables that they can safely predict, thus taking some of the sting out of the fiducial idea. By restricting probabilistic inference to safe uses, one also automatically avoids paradoxes such as the Monty Hall problem. Safety comes in a variety of degrees, such as “validity” (the strongest notion), “calibration”, “confidence safety” and “unbiasedness” (almost the weakest notion). \|
Tasks	Calibration
Published	2016-04-06
URL	http://arxiv.org/abs/1604.01785v1
PDF	http://arxiv.org/pdf/1604.01785v1.pdf
PWC	https://paperswithcode.com/paper/safe-probability
Repo
Framework

PSDVec: a Toolbox for Incremental and Scalable Word Embedding


Title	PSDVec: a Toolbox for Incremental and Scalable Word Embedding
Authors	Shaohua Li, Jun Zhu, Chunyan Miao
Abstract	PSDVec is a Python/Perl toolbox that learns word embeddings, i.e. the mapping of words in a natural language to continuous vectors which encode the semantic/syntactic regularities between the words. PSDVec implements a word embedding learning method based on a weighted low-rank positive semidefinite approximation. To scale up the learning process, we implement a blockwise online learning algorithm to learn the embeddings incrementally. This strategy greatly reduces the learning time of word embeddings on a large vocabulary, and can learn the embeddings of new words without re-learning the whole vocabulary. On 9 word similarity/analogy benchmark sets and 2 Natural Language Processing (NLP) tasks, PSDVec produces embeddings that has the best average performance among popular word embedding tools. PSDVec provides a new option for NLP practitioners.
Tasks	Word Embeddings
Published	2016-06-10
URL	http://arxiv.org/abs/1606.03192v1
PDF	http://arxiv.org/pdf/1606.03192v1.pdf
PWC	https://paperswithcode.com/paper/psdvec-a-toolbox-for-incremental-and-scalable
Repo
Framework

The Evolutionary Process of Image Transition in Conjunction with Box and Strip Mutation


Title	The Evolutionary Process of Image Transition in Conjunction with Box and Strip Mutation
Authors	Aneta Neumann, Bradley Alexander, Frank Neumann
Abstract	Evolutionary algorithms have been used in many ways to generate digital art. We study how evolutionary processes are used for evolutionary art and present a new approach to the transition of images. Our main idea is to define evolutionary processes for digital image transition, combining different variants of mutation and evolutionary mechanisms. We introduce box and strip mutation operators which are specifically designed for image transition. Our experimental results show that the process of an evolutionary algorithm in combination with these mutation operators can be used as a valuable way to produce unique generative art.
Tasks
Published	2016-08-05
URL	http://arxiv.org/abs/1608.01783v1
PDF	http://arxiv.org/pdf/1608.01783v1.pdf
PWC	https://paperswithcode.com/paper/the-evolutionary-process-of-image-transition
Repo
Framework

Interactive Tools and Tasks for the Hebrew Bible


Title	Interactive Tools and Tasks for the Hebrew Bible
Authors	Nicolai Winther-Nielsen
Abstract	This contribution to a special issue on “Computer-aided processing of intertextuality” in ancient texts will illustrate how using digital tools to interact with the Hebrew Bible offers new promising perspectives for visualizing the texts and for performing tasks in education and research. This contribution explores how the corpus of the Hebrew Bible created and maintained by the Eep Talstra Centre for Bible and Computer can support new methods for modern knowledge workers within the field of digital humanities and theology be applied to ancient texts, and how this can be envisioned as a new field of digital intertextuality. The article first describes how the corpus was used to develop the Bible Online Learner as a persuasive technology to enhance language learning with, in, and around a database that acts as the engine driving interactive tasks for learners. Intertextuality in this case is a matter of active exploration and ongoing practice. Furthermore, interactive corpus-technology has an important bearing on the task of textual criticism as a specialized area of research that depends increasingly on the availability of digital resources. Commercial solutions developed by software companies like Logos and Accordance offer a market-based intertextuality defined by the production of advanced digital resources for scholars and students as useful alternatives to often inaccessible and expensive printed versions. It is reasonable to expect that in the future interactive corpus technology will allow scholars to do innovative academic tasks in textual criticism and interpretation. We have already seen the emergence of promising tools for text categorization, analysis of translation shifts, and interpretation. Broadly speaking, interactive tools and tasks within the three areas of language learning, textual criticism, and Biblical studies illustrate a new kind of intertextuality emerging within digital humanities.
Tasks	Text Categorization
Published	2016-03-14
URL	http://arxiv.org/abs/1603.04236v5
PDF	http://arxiv.org/pdf/1603.04236v5.pdf
PWC	https://paperswithcode.com/paper/interactive-tools-and-tasks-for-the-hebrew
Repo
Framework

Complex Decomposition of the Negative Distance kernel


Title	Complex Decomposition of the Negative Distance kernel
Authors	Tim vor der Brück, Steffen Eger, Alexander Mehler
Abstract	A Support Vector Machine (SVM) has become a very popular machine learning method for text classification. One reason for this relates to the range of existing kernels which allow for classifying data that is not linearly separable. The linear, polynomial and RBF (Gaussian Radial Basis Function) kernel are commonly used and serve as a basis of comparison in our study. We show how to derive the primal form of the quadratic Power Kernel (PK) – also called the Negative Euclidean Distance Kernel (NDK) – by means of complex numbers. We exemplify the NDK in the framework of text categorization using the Dewey Document Classification (DDC) as the target scheme. Our evaluation shows that the power kernel produces F-scores that are comparable to the reference kernels, but is – except for the linear kernel – faster to compute. Finally, we show how to extend the NDK-approach by including the Mahalanobis distance.
Tasks	Document Classification, Text Categorization, Text Classification
Published	2016-01-05
URL	http://arxiv.org/abs/1601.00925v1
PDF	http://arxiv.org/pdf/1601.00925v1.pdf
PWC	https://paperswithcode.com/paper/complex-decomposition-of-the-negative
Repo
Framework

Small-footprint Highway Deep Neural Networks for Speech Recognition


Title	Small-footprint Highway Deep Neural Networks for Speech Recognition
Authors	Liang Lu, Steve Renals
Abstract	State-of-the-art speech recognition systems typically employ neural network acoustic models. However, compared to Gaussian mixture models, deep neural network (DNN) based acoustic models often have many more model parameters, making it challenging for them to be deployed on resource-constrained platforms, such as mobile devices. In this paper, we study the application of the recently proposed highway deep neural network (HDNN) for training small-footprint acoustic models. HDNNs are a depth-gated feedforward neural network, which include two types of gate functions to facilitate the information flow through different layers. Our study demonstrates that HDNNs are more compact than regular DNNs for acoustic modeling, i.e., they can achieve comparable recognition accuracy with many fewer model parameters. Furthermore, HDNNs are more controllable than DNNs: the gate functions of an HDNN can control the behavior of the whole network using a very small number of model parameters. Finally, we show that HDNNs are more adaptable than DNNs. For example, simply updating the gate functions using adaptation data can result in considerable gains in accuracy. We demonstrate these aspects by experiments using the publicly available AMI corpus, which has around 80 hours of training data.
Tasks	Speech Recognition
Published	2016-10-18
URL	http://arxiv.org/abs/1610.05812v4
PDF	http://arxiv.org/pdf/1610.05812v4.pdf
PWC	https://paperswithcode.com/paper/small-footprint-highway-deep-neural-networks
Repo
Framework

Recurrent Attentional Networks for Saliency Detection


Title	Recurrent Attentional Networks for Saliency Detection
Authors	Jason Kuen, Zhenhua Wang, Gang Wang
Abstract	Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection. But, they do not work well with objects of multiple scales. To overcome such a limitation, in this work, we propose a recurrent attentional convolutional-deconvolution network (RACDNN). Using spatial transformer and recurrent network units, RACDNN is able to iteratively attend to selected image sub-regions to perform saliency refinement progressively. Besides tackling the scale problem, RACDNN can also learn context-aware features from past iterations to enhance saliency refinement in future iterations. Experiments on several challenging saliency detection datasets validate the effectiveness of RACDNN, and show that RACDNN outperforms state-of-the-art saliency detection methods.
Tasks	Saliency Detection
Published	2016-04-12
URL	http://arxiv.org/abs/1604.03227v1
PDF	http://arxiv.org/pdf/1604.03227v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-attentional-networks-for-saliency
Repo
Framework

A Local Density-Based Approach for Local Outlier Detection


Title	A Local Density-Based Approach for Local Outlier Detection
Authors	Bo Tang, Haibo He
Abstract	This paper presents a simple but effective density-based outlier detection approach with the local kernel density estimation (KDE). A Relative Density-based Outlier Score (RDOS) is introduced to measure the local outlierness of objects, in which the density distribution at the location of an object is estimated with a local KDE method based on extended nearest neighbors of the object. Instead of using only $k$ nearest neighbors, we further consider reverse nearest neighbors and shared nearest neighbors of an object for density distribution estimation. Some theoretical properties of the proposed RDOS including its expected value and false alarm probability are derived. A comprehensive experimental study on both synthetic and real-life data sets demonstrates that our approach is more effective than state-of-the-art outlier detection methods.
Tasks	Density Estimation, Outlier Detection
Published	2016-06-28
URL	http://arxiv.org/abs/1606.08538v1
PDF	http://arxiv.org/pdf/1606.08538v1.pdf
PWC	https://paperswithcode.com/paper/a-local-density-based-approach-for-local
Repo
Framework

A vector-contraction inequality for Rademacher complexities


Title	A vector-contraction inequality for Rademacher complexities
Authors	Andreas Maurer
Abstract	The contraction inequality for Rademacher averages is extended to Lipschitz functions with vector-valued domains, and it is also shown that in the bounding expression the Rademacher variables can be replaced by arbitrary iid symmetric and sub-gaussian variables. Example applications are given for multi-category learning, K-means clustering and learning-to-learn.
Tasks
Published	2016-05-01
URL	http://arxiv.org/abs/1605.00251v1
PDF	http://arxiv.org/pdf/1605.00251v1.pdf
PWC	https://paperswithcode.com/paper/a-vector-contraction-inequality-for
Repo
Framework

Robust LSTM-Autoencoders for Face De-Occlusion in the Wild


Title	Robust LSTM-Autoencoders for Face De-Occlusion in the Wild
Authors	Fang Zhao, Jiashi Feng, Jian Zhao, Wenhan Yang, Shuicheng Yan
Abstract	Face recognition techniques have been developed significantly in recent years. However, recognizing faces with partial occlusion is still challenging for existing face recognizers which is heavily desired in real-world applications concerning surveillance and security. Although much research effort has been devoted to developing face de-occlusion methods, most of them can only work well under constrained conditions, such as all the faces are from a pre-defined closed set. In this paper, we propose a robust LSTM-Autoencoders (RLA) model to effectively restore partially occluded faces even in the wild. The RLA model consists of two LSTM components, which aims at occlusion-robust face encoding and recurrent occlusion removal respectively. The first one, named multi-scale spatial LSTM encoder, reads facial patches of various scales sequentially to output a latent representation, and occlusion-robustness is achieved owing to the fact that the influence of occlusion is only upon some of the patches. Receiving the representation learned by the encoder, the LSTM decoder with a dual channel architecture reconstructs the overall face and detects occlusion simultaneously, and by feat of LSTM, the decoder breaks down the task of face de-occlusion into restoring the occluded part step by step. Moreover, to minimize identify information loss and guarantee face recognition accuracy over recovered faces, we introduce an identity-preserving adversarial training scheme to further improve RLA. Extensive experiments on both synthetic and real datasets of faces with occlusion clearly demonstrate the effectiveness of our proposed RLA in removing different types of facial occlusion at various locations. The proposed method also provides significantly larger performance gain than other de-occlusion methods in promoting recognition performance over partially-occluded faces.
Tasks	Face Recognition
Published	2016-12-27
URL	http://arxiv.org/abs/1612.08534v1
PDF	http://arxiv.org/pdf/1612.08534v1.pdf
PWC	https://paperswithcode.com/paper/robust-lstm-autoencoders-for-face-de
Repo
Framework

Automated X-ray Image Analysis for Cargo Security: Critical Review and Future Promise


Title	Automated X-ray Image Analysis for Cargo Security: Critical Review and Future Promise
Authors	Thomas W. Rogers, Nicolas Jaccard, Edward J. Morton, Lewis D. Griffin
Abstract	We review the relatively immature field of automated image analysis for X-ray cargo imagery. There is increasing demand for automated analysis methods that can assist in the inspection and selection of containers, due to the ever-growing volumes of traded cargo and the increasing concerns that customs- and security-related threats are being smuggled across borders by organised crime and terrorist networks. We split the field into the classical pipeline of image preprocessing and image understanding. Preprocessing includes: image manipulation; quality improvement; Threat Image Projection (TIP); and material discrimination and segmentation. Image understanding includes: Automated Threat Detection (ATD); and Automated Contents Verification (ACV). We identify several gaps in the literature that need to be addressed and propose ideas for future research. Where the current literature is sparse we borrow from the single-view, multi-view, and CT X-ray baggage domains, which have some characteristics in common with X-ray cargo.
Tasks
Published	2016-08-02
URL	http://arxiv.org/abs/1608.01017v1
PDF	http://arxiv.org/pdf/1608.01017v1.pdf
PWC	https://paperswithcode.com/paper/automated-x-ray-image-analysis-for-cargo
Repo
Framework

Automatic Detection of Epileptiform Discharges in the EEG


Title	Automatic Detection of Epileptiform Discharges in the EEG
Authors	Andre Rosado, Agostinho C Rosa
Abstract	The diagnosis of epilepsy generally includes a visual inspection of EEG recorded data by the Neurologist, with the purpose of checking the occurrence of transient waveforms called interictal epileptiform discharges. These waveforms have short duration (less than 100 ms), so the inspection process is usually time-consuming, particularly for ambulatory long term EEG records. Therefore, an automatic detection system of epileptiform discharges can be a valuable tool for a Neurology service. The proposed approach is the development of a multi stage detection algorithm, which processes the complete EEG signals and applies decision criteria to selected waveforms. It employs EEG analysis techniques such as Wavelet Transform and Mimetic Analysis, complemented with a classification based on Fuzzy Logic. In order to evaluate the algorithm’s performance, data were collected from several epileptic patients, with epileptiform activity marked by a Neurologist. The average values obtained for both Sensitivity and Specificity were respectively higher than 80 and 70 percent.
Tasks	EEG
Published	2016-05-21
URL	http://arxiv.org/abs/1605.06708v1
PDF	http://arxiv.org/pdf/1605.06708v1.pdf
PWC	https://paperswithcode.com/paper/automatic-detection-of-epileptiform
Repo
Framework