May 6, 2019

2920 words 14 mins read

Paper Group ANR 191

A global optimization algorithm for sparse mixed membership matrix factorization. Axiomatizing Category Theory in Free Logic. NoiseOut: A Simple Way to Prune Neural Networks. Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian. Transition-based versus State-based Reward Functions for MDPs with Value-at-Risk. Deep Reinforcement Lear …

A global optimization algorithm for sparse mixed membership matrix factorization


Title	A global optimization algorithm for sparse mixed membership matrix factorization
Authors	Fan Zhang, Chuangqi Wang, Andrew Trapp, Patrick Flaherty
Abstract	Mixed membership factorization is a popular approach for analyzing data sets that have within-sample heterogeneity. In recent years, several algorithms have been developed for mixed membership matrix factorization, but they only guarantee estimates from a local optimum. Here, we derive a global optimization (GOP) algorithm that provides a guaranteed $\epsilon$-global optimum for a sparse mixed membership matrix factorization problem. We test the algorithm on simulated data and find the algorithm always bounds the global optimum across random initializations and explores multiple modes efficiently.
Tasks
Published	2016-10-19
URL	http://arxiv.org/abs/1610.06145v2
PDF	http://arxiv.org/pdf/1610.06145v2.pdf
PWC	https://paperswithcode.com/paper/a-global-optimization-algorithm-for-sparse
Repo
Framework

Axiomatizing Category Theory in Free Logic


Title	Axiomatizing Category Theory in Free Logic
Authors	Christoph Benzmüller, Dana S. Scott
Abstract	Starting from a generalization of the standard axioms for a monoid we present a stepwise development of various, mutually equivalent foundational axiom systems for category theory. Our axiom sets have been formalized in the Isabelle/HOL interactive proof assistant, and this formalization utilizes a semantically correct embedding of free logic in classical higher-order logic. The modeling and formal analysis of our axiom sets has been significantly supported by series of experiments with automated reasoning tools integrated with Isabelle/HOL. We also address the relation of our axiom systems to alternative proposals from the literature, including an axiom set proposed by Freyd and Scedrov for which we reveal a technical issue (when encoded in free logic where free variables range over defined and undefined objects): either all operations, e.g. morphism composition, are total or their axiom system is inconsistent. The repair for this problem is quite straightforward, however.
Tasks
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01493v5
PDF	http://arxiv.org/pdf/1609.01493v5.pdf
PWC	https://paperswithcode.com/paper/axiomatizing-category-theory-in-free-logic
Repo
Framework

NoiseOut: A Simple Way to Prune Neural Networks


Title	NoiseOut: A Simple Way to Prune Neural Networks
Authors	Mohammad Babaeizadeh, Paris Smaragdis, Roy H. Campbell
Abstract	Neural networks are usually over-parameterized with significant redundancy in the number of required neurons which results in unnecessary computation and memory usage at inference time. One common approach to address this issue is to prune these big networks by removing extra neurons and parameters while maintaining the accuracy. In this paper, we propose NoiseOut, a fully automated pruning algorithm based on the correlation between activations of neurons in the hidden layers. We prove that adding additional output neurons with entirely random targets results into a higher correlation between neurons which makes pruning by NoiseOut even more efficient. Finally, we test our method on various networks and datasets. These experiments exhibit high pruning rates while maintaining the accuracy of the original network.
Tasks
Published	2016-11-18
URL	http://arxiv.org/abs/1611.06211v1
PDF	http://arxiv.org/pdf/1611.06211v1.pdf
PWC	https://paperswithcode.com/paper/noiseout-a-simple-way-to-prune-neural
Repo
Framework

Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian


Title	Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian
Authors	Thanh-Toan Do, Anh-Dzung Doan, Duc-Thanh Nguyen, Ngai-Man Cheung
Abstract	This paper proposes two approaches for inferencing binary codes in two-step (supervised, unsupervised) hashing. We first introduce an unified formulation for both supervised and unsupervised hashing. Then, we cast the learning of one bit as a Binary Quadratic Problem (BQP). We propose two approaches to solve BQP. In the first approach, we relax BQP as a semidefinite programming problem which its global optimum can be achieved. We theoretically prove that the objective value of the binary solution achieved by this approach is well bounded. In the second approach, we propose an augmented Lagrangian based approach to solve BQP directly without relaxing the binary constraint. Experimental results on three benchmark datasets show that our proposed methods compare favorably with the state of the art.
Tasks
Published	2016-07-19
URL	http://arxiv.org/abs/1607.05396v1
PDF	http://arxiv.org/pdf/1607.05396v1.pdf
PWC	https://paperswithcode.com/paper/binary-hashing-with-semidefinite-relaxation
Repo
Framework

Transition-based versus State-based Reward Functions for MDPs with Value-at-Risk


Title	Transition-based versus State-based Reward Functions for MDPs with Value-at-Risk
Authors	Shuai Ma, Jia Yuan Yu
Abstract	In reinforcement learning, the reward function on current state and action is widely used. When the objective is about the expectation of the (discounted) total reward only, it works perfectly. However, if the objective involves the total reward distribution, the result will be wrong. This paper studies Value-at-Risk (VaR) problems in short- and long-horizon Markov decision processes (MDPs) with two reward functions, which share the same expectations. Firstly we show that with VaR objective, when the real reward function is transition-based (with respect to action and both current and next states), the simplified (state-based, with respect to action and current state only) reward function will change the VaR. Secondly, for long-horizon MDPs, we estimate the VaR function with the aid of spectral theory and the central limit theorem. Thirdly, since the estimation method is for a Markov reward process with the reward function on current state only, we present a transformation algorithm for the Markov reward process with the reward function on current and next states, in order to estimate the VaR function with an intact total reward distribution.
Tasks
Published	2016-12-07
URL	http://arxiv.org/abs/1612.02088v4
PDF	http://arxiv.org/pdf/1612.02088v4.pdf
PWC	https://paperswithcode.com/paper/transition-based-versus-state-based-reward
Repo
Framework

Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates


Title	Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates
Authors	Shixiang Gu, Ethan Holly, Timothy Lillicrap, Sergey Levine
Abstract	Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered policy representations and human-supplied demonstrations. Deep reinforcement learning alleviates this limitation by training general-purpose neural network policies, but applications of direct deep reinforcement learning algorithms have so far been restricted to simulated settings and relatively simple tasks, due to their apparent high sample complexity. In this paper, we demonstrate that a recent deep reinforcement learning algorithm based on off-policy training of deep Q-functions can scale to complex 3D manipulation tasks and can learn deep neural network policies efficiently enough to train on real physical robots. We demonstrate that the training times can be further reduced by parallelizing the algorithm across multiple robots which pool their policy updates asynchronously. Our experimental evaluation shows that our method can learn a variety of 3D manipulation skills in simulation and a complex door opening skill on real robots without any prior demonstrations or manually designed representations.
Tasks
Published	2016-10-03
URL	http://arxiv.org/abs/1610.00633v2
PDF	http://arxiv.org/pdf/1610.00633v2.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-for-robotic
Repo
Framework

Finding Street Gang Members on Twitter


Title	Finding Street Gang Members on Twitter
Authors	Lakshika Balasuriya, Sanjaya Wijeratne, Derek Doran, Amit Sheth
Abstract	Most street gang members use Twitter to intimidate others, to present outrageous images and statements to the world, and to share recent illegal activities. Their tweets may thus be useful to law enforcement agencies to discover clues about recent crimes or to anticipate ones that may occur. Finding these posts, however, requires a method to discover gang member Twitter profiles. This is a challenging task since gang members represent a very small population of the 320 million Twitter users. This paper studies the problem of automatically finding gang members on Twitter. It outlines a process to curate one of the largest sets of verifiable gang member profiles that have ever been studied. A review of these profiles establishes differences in the language, images, YouTube links, and emojis gang members use compared to the rest of the Twitter population. Features from this review are used to train a series of supervised classifiers. Our classifier achieves a promising F1 score with a low false positive rate.
Tasks
Published	2016-10-29
URL	http://arxiv.org/abs/1610.09516v1
PDF	http://arxiv.org/pdf/1610.09516v1.pdf
PWC	https://paperswithcode.com/paper/finding-street-gang-members-on-twitter
Repo
Framework

NCBO Ontology Recommender 2.0: An Enhanced Approach for Biomedical Ontology Recommendation


Title	NCBO Ontology Recommender 2.0: An Enhanced Approach for Biomedical Ontology Recommendation
Authors	Marcos Martinez-Romero, Clement Jonquet, Martin J. O’Connor, John Graybeal, Alejandro Pazos, Mark A. Musen
Abstract	Biomedical researchers use ontologies to annotate their data with ontology terms, enabling better data integration and interoperability. However, the number, variety and complexity of current biomedical ontologies make it cumbersome for researchers to determine which ones to reuse for their specific needs. To overcome this problem, in 2010 the National Center for Biomedical Ontology (NCBO) released the Ontology Recommender, which is a service that receives a biomedical text corpus or a list of keywords and suggests ontologies appropriate for referencing the indicated terms. We developed a new version of the NCBO Ontology Recommender. Called Ontology Recommender 2.0, it uses a new recommendation approach that evaluates the relevance of an ontology to biomedical text data according to four criteria: (1) the extent to which the ontology covers the input data; (2) the acceptance of the ontology in the biomedical community; (3) the level of detail of the ontology classes that cover the input data; and (4) the specialization of the ontology to the domain of the input data. Our evaluation shows that the enhanced recommender provides higher quality suggestions than the original approach, providing better coverage of the input data, more detailed information about their concepts, increased specialization for the domain of the input data, and greater acceptance and use in the community. In addition, it provides users with more explanatory information, along with suggestions of not only individual ontologies but also groups of ontologies. It also can be customized to fit the needs of different scenarios. Ontology Recommender 2.0 combines the strengths of its predecessor with a range of adjustments and new features that improve its reliability and usefulness. Ontology Recommender 2.0 recommends over 500 biomedical ontologies from the NCBO BioPortal platform, where it is openly available.
Tasks
Published	2016-11-18
URL	http://arxiv.org/abs/1611.05973v2
PDF	http://arxiv.org/pdf/1611.05973v2.pdf
PWC	https://paperswithcode.com/paper/ncbo-ontology-recommender-20-an-enhanced
Repo
Framework

Increasing the throughput of machine translation systems using clouds


Title	Increasing the throughput of machine translation systems using clouds
Authors	Jernej Vičič, Andrej Brodnik
Abstract	The manuscript presents an experiment at implementation of a Machine Translation system in a MapReduce model. The empirical evaluation was done using fully implemented translation systems embedded into the MapReduce programming model. Two machine translation paradigms were studied: shallow transfer Rule Based Machine Translation and Statistical Machine Translation. The results show that the MapReduce model can be successfully used to increase the throughput of a machine translation system. Furthermore this method enhances the throughput of a machine translation system without decreasing the quality of the translation output. Thus, the present manuscript also represents a contribution to the seminal work in natural language processing, specifically Machine Translation. It first points toward the importance of the definition of the metric of throughput of translation system and, second, the applicability of the machine translation task to the MapReduce paradigm.
Tasks	Machine Translation
Published	2016-11-09
URL	http://arxiv.org/abs/1611.02944v1
PDF	http://arxiv.org/pdf/1611.02944v1.pdf
PWC	https://paperswithcode.com/paper/increasing-the-throughput-of-machine
Repo
Framework

Maximizing positive opinion influence using an evidential approach


Title	Maximizing positive opinion influence using an evidential approach
Authors	Siwar Jendoubi, Arnaud Martin, Ludovic Liétard, Hend Hadji, Boutheina Yaghlane
Abstract	In this paper, we propose a new data based model for influence maximization in online social networks. We use the theory of belief functions to overcome the data imperfection problem. Besides, the proposed model searches to detect influencer users that adopt a positive opinion about the product, the idea, etc, to be propagated. Moreover, we present some experiments to show the performance of our model.
Tasks
Published	2016-10-20
URL	http://arxiv.org/abs/1610.06340v1
PDF	http://arxiv.org/pdf/1610.06340v1.pdf
PWC	https://paperswithcode.com/paper/maximizing-positive-opinion-influence-using
Repo
Framework

Locally-Supervised Deep Hybrid Model for Scene Recognition


Title	Locally-Supervised Deep Hybrid Model for Scene Recognition
Authors	Sheng Guo, Weilin Huang, Limin Wang, Yu Qiao
Abstract	Convolutional neural networks (CNN) have recently achieved remarkable successes in various image classification and understanding tasks. The deep features obtained at the top fully-connected layer of the CNN (FC-features) exhibit rich global semantic information and are extremely effective in image classification. On the other hand, the convolutional features in the middle layers of the CNN also contain meaningful local information, but are not fully explored for image representation. In this paper, we propose a novel Locally-Supervised Deep Hybrid Model (LS-DHM) that effectively enhances and explores the convolutional features for scene recognition. Firstly, we notice that the convolutional features capture local objects and fine structures of scene images, which yield important cues for discriminating ambiguous scenes, whereas these features are significantly eliminated in the highly-compressed FC representation. Secondly, we propose a new Local Convolutional Supervision (LCS) layer to enhance the local structure of the image by directly propagating the label information to the convolutional layers. Thirdly, we propose an efficient Fisher Convolutional Vector (FCV) that successfully rescues the orderless mid-level semantic information (e.g. objects and textures) of scene image. The FCV encodes the large-sized convolutional maps into a fixed-length mid-level representation, and is demonstrated to be strongly complementary to the high-level FC-features. Finally, both the FCV and FC-features are collaboratively employed in the LSDHM representation, which achieves outstanding performance in our experiments. It obtains 83.75% and 67.56% accuracies respectively on the heavily benchmarked MIT Indoor67 and SUN397 datasets, advancing the stat-of-the-art substantially.
Tasks	Image Classification, Scene Recognition
Published	2016-01-27
URL	http://arxiv.org/abs/1601.07576v2
PDF	http://arxiv.org/pdf/1601.07576v2.pdf
PWC	https://paperswithcode.com/paper/locally-supervised-deep-hybrid-model-for
Repo
Framework

Modelling Temporal Information Using Discrete Fourier Transform for Recognizing Emotions in User-generated Videos


Title	Modelling Temporal Information Using Discrete Fourier Transform for Recognizing Emotions in User-generated Videos
Authors	Haimin Zhang, Min Xu
Abstract	With the widespread of user-generated Internet videos, emotion recognition in those videos attracts increasing research efforts. However, most existing works are based on framelevel visual features and/or audio features, which might fail to model the temporal information, e.g. characteristics accumulated along time. In order to capture video temporal information, in this paper, we propose to analyse features in frequency domain transformed by discrete Fourier transform (DFT features). Frame-level features are firstly extract by a pre-trained deep convolutional neural network (CNN). Then, time domain features are transferred and interpolated into DFT features. CNN and DFT features are further encoded and fused for emotion classification. By this way, static image features extracted from a pre-trained deep CNN and temporal information represented by DFT features are jointly considered for video emotion recognition. Experimental results demonstrate that combining DFT features can effectively capture temporal information and therefore improve emotion recognition performance. Our approach has achieved a state-of-the-art performance on the largest video emotion dataset (VideoEmotion-8 dataset), improving accuracy from 51.1% to 62.6%.
Tasks	Emotion Classification, Emotion Recognition, Video Emotion Recognition
Published	2016-03-20
URL	http://arxiv.org/abs/1603.06568v2
PDF	http://arxiv.org/pdf/1603.06568v2.pdf
PWC	https://paperswithcode.com/paper/modelling-temporal-information-using-discrete
Repo
Framework

Hierarchical Linearly-Solvable Markov Decision Problems


Title	Hierarchical Linearly-Solvable Markov Decision Problems
Authors	Anders Jonsson, Vicenç Gómez
Abstract	We present a hierarchical reinforcement learning framework that formulates each task in the hierarchy as a special type of Markov decision process for which the Bellman equation is linear and has analytical solution. Problems of this type, called linearly-solvable MDPs (LMDPs) have interesting properties that can be exploited in a hierarchical setting, such as efficient learning of the optimal value function or task compositionality. The proposed hierarchical approach can also be seen as a novel alternative to solving LMDPs with large state spaces. We derive a hierarchical version of the so-called Z-learning algorithm that learns different tasks simultaneously and show empirically that it significantly outperforms the state-of-the-art learning methods in two classical hierarchical reinforcement learning domains: the taxi domain and an autonomous guided vehicle task.
Tasks	Hierarchical Reinforcement Learning
Published	2016-03-10
URL	http://arxiv.org/abs/1603.03267v1
PDF	http://arxiv.org/pdf/1603.03267v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-linearly-solvable-markov
Repo
Framework

Local feature hierarchy for face recognition across pose and illumination


Title	Local feature hierarchy for face recognition across pose and illumination
Authors	Xiaoyue Jiang, Dong Zhang, Xiaoyi Feng
Abstract	Even though face recognition in frontal view and normal lighting condition works very well, the performance degenerates sharply in extreme conditions. Recently there are many work dealing with pose and illumination problems, respectively. However both the lighting and pose variation will always be encountered at the same time. Accordingly we propose an end-to-end face recognition method to deal with pose and illumination simultaneously based on convolutional networks where the discriminative nonlinear features that are invariant to pose and illumination are extracted. Normally the global structure for images taken in different views is quite diverse. Therefore we propose to use the 11 convolutional kernel to extract the local features. Furthermore the parallel multi-stream multi-layer 11 convolution network is developed to extract multi-hierarchy features. In the experiments we obtained the average face recognition rate of 96.9% on multiPIE dataset,which improves the state-of-the-art of face recognition across poses and illumination by 7.5%. Especially for profile-wise positions, the average recognition rate of our proposed network is 97.8%, which increases the state-of-the-art recognition rate by 19%.
Tasks	Face Recognition
Published	2016-07-12
URL	http://arxiv.org/abs/1607.03226v1
PDF	http://arxiv.org/pdf/1607.03226v1.pdf
PWC	https://paperswithcode.com/paper/local-feature-hierarchy-for-face-recognition
Repo
Framework

Multi-View Treelet Transform


Title	Multi-View Treelet Transform
Authors	Brian A. Mitchell, Linda R. Petzold
Abstract	Current multi-view factorization methods make assumptions that are not acceptable for many kinds of data, and in particular, for graphical data with hierarchical structure. At the same time, current hierarchical methods work only in the single-view setting. We generalize the Treelet Transform to the Multi-View Treelet Transform (MVTT) to allow for the capture of hierarchical structure when multiple views are available. Further, we show how this generalization is consistent with the existing theory and how it might be used in denoising empirical networks and in computing the shared response of functional brain data.
Tasks	Denoising
Published	2016-06-02
URL	http://arxiv.org/abs/1606.00800v2
PDF	http://arxiv.org/pdf/1606.00800v2.pdf
PWC	https://paperswithcode.com/paper/multi-view-treelet-transform
Repo
Framework