July 28, 2019

2740 words 13 mins read

Paper Group ANR 167

Marginal likelihood based model comparison in Fuzzy Bayesian Learning. RedDwarfData: a simplified dataset of StarCraft matches. Parallel Active Subspace Decomposition for Scalable and Efficient Tensor Robust Principal Component Analysis. Learning High Dynamic Range from Outdoor Panoramas. A Machine Learning Approach to Modeling Human Migration. Fas …

Marginal likelihood based model comparison in Fuzzy Bayesian Learning


Title	Marginal likelihood based model comparison in Fuzzy Bayesian Learning
Authors	Indranil Pan, Dirk Bester
Abstract	In a recent paper [1] we introduced the Fuzzy Bayesian Learning (FBL) paradigm where expert opinions can be encoded in the form of fuzzy rule bases and the hyper-parameters of the fuzzy sets can be learned from data using a Bayesian approach. The present paper extends this work for selecting the most appropriate rule base among a set of competing alternatives, which best explains the data, by calculating the model evidence or marginal likelihood. We explain why this is an attractive alternative over simply minimizing a mean squared error metric of prediction and show the validity of the proposition using synthetic examples and a real world case study in the financial services sector.
Tasks
Published	2017-03-29
URL	http://arxiv.org/abs/1703.09956v1
PDF	http://arxiv.org/pdf/1703.09956v1.pdf
PWC	https://paperswithcode.com/paper/marginal-likelihood-based-model-comparison-in
Repo
Framework

RedDwarfData: a simplified dataset of StarCraft matches


Title	RedDwarfData: a simplified dataset of StarCraft matches
Authors	Juan J. Merelo-Guervós, Antonio Fernández-Ares, Antonio Álvarez Caballero, Pablo García-Sánchez, Victor Rivas
Abstract	The game Starcraft is one of the most interesting arenas to test new machine learning and computational intelligence techniques; however, StarCraft matches take a long time and creating a good dataset for training can be hard. Besides, analyzing match logs to extract the main characteristics can also be done in many different ways to the point that extracting and processing data itself can take an inordinate amount of time and of course, depending on what you choose, can bias learning algorithms. In this paper we present a simplified dataset extracted from the set of matches published by Robinson and Watson, which we have called RedDwarfData, containing several thousand matches processed to frames, so that temporal studies can also be undertaken. This dataset is available from GitHub under a free license. An initial analysis and appraisal of these matches is also made.
Tasks	Starcraft
Published	2017-12-29
URL	http://arxiv.org/abs/1712.10179v1
PDF	http://arxiv.org/pdf/1712.10179v1.pdf
PWC	https://paperswithcode.com/paper/reddwarfdata-a-simplified-dataset-of
Repo
Framework

Parallel Active Subspace Decomposition for Scalable and Efficient Tensor Robust Principal Component Analysis


Title	Parallel Active Subspace Decomposition for Scalable and Efficient Tensor Robust Principal Component Analysis
Authors	Jonathan Q. Jiang, Michael K. Ng
Abstract	Tensor robust principal component analysis (TRPCA) has received a substantial amount of attention in various fields. Most existing methods, normally relying on tensor nuclear norm minimization, need to pay an expensive computational cost due to multiple singular value decompositions (SVDs) at each iteration. To overcome the drawback, we propose a scalable and efficient method, named Parallel Active Subspace Decomposition (PASD), which divides the unfolding along each mode of the tensor into a columnwise orthonormal matrix (active subspace) and another small-size matrix in parallel. Such a transformation leads to a nonconvex optimization problem in which the scale of nulcear norm minimization is generally much smaller than that in the original problem. Furthermore, we introduce an alternating direction method of multipliers (ADMM) method to solve the reformulated problem and provide rigorous analyses for its convergence and suboptimality. Experimental results on synthetic and real-world data show that our algorithm is more accurate than the state-of-the-art approaches, and is orders of magnitude faster.
Tasks
Published	2017-12-28
URL	http://arxiv.org/abs/1712.09999v1
PDF	http://arxiv.org/pdf/1712.09999v1.pdf
PWC	https://paperswithcode.com/paper/parallel-active-subspace-decomposition-for
Repo
Framework

Learning High Dynamic Range from Outdoor Panoramas


Title	Learning High Dynamic Range from Outdoor Panoramas
Authors	Jinsong Zhang, Jean-François Lalonde
Abstract	Outdoor lighting has extremely high dynamic range. This makes the process of capturing outdoor environment maps notoriously challenging since special equipment must be used. In this work, we propose an alternative approach. We first capture lighting with a regular, LDR omnidirectional camera, and aim to recover the HDR after the fact via a novel, learning-based inverse tonemapping method. We propose a deep autoencoder framework which regresses linear, high dynamic range data from non-linear, saturated, low dynamic range panoramas. We validate our method through a wide set of experiments on synthetic data, as well as on a novel dataset of real photographs with ground truth. Our approach finds applications in a variety of settings, ranging from outdoor light capture to image matching.
Tasks
Published	2017-03-29
URL	http://arxiv.org/abs/1703.10200v4
PDF	http://arxiv.org/pdf/1703.10200v4.pdf
PWC	https://paperswithcode.com/paper/learning-high-dynamic-range-from-outdoor
Repo
Framework

A Machine Learning Approach to Modeling Human Migration


Title	A Machine Learning Approach to Modeling Human Migration
Authors	Caleb Robinson, Bistra Dilkina
Abstract	Human migration is a type of human mobility, where a trip involves a person moving with the intention of changing their home location. Predicting human migration as accurately as possible is important in city planning applications, international trade, spread of infectious diseases, conservation planning, and public policy development. Traditional human mobility models, such as gravity models or the more recent radiation model, predict human mobility flows based on population and distance features only. These models have been validated on commuting flows, a different type of human mobility, and are mainly used in modeling scenarios where large amounts of prior ground truth mobility data are not available. One downside of these models is that they have a fixed form and are therefore not able to capture more complicated migration dynamics. We propose machine learning models that are able to incorporate any number of exogenous features, to predict origin/destination human migration flows. Our machine learning models outperform traditional human mobility models on a variety of evaluation metrics, both in the task of predicting migrations between US counties as well as international migrations. In general, predictive machine learning models of human migration will provide a flexible base with which to model human migration under different what-if conditions, such as potential sea level rise or population growth scenarios.
Tasks
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05462v1
PDF	http://arxiv.org/pdf/1711.05462v1.pdf
PWC	https://paperswithcode.com/paper/a-machine-learning-approach-to-modeling-human
Repo
Framework

Fast calculation of entropy with Zhang’s estimator


Title	Fast calculation of entropy with Zhang’s estimator
Authors	Antoni Lozano, Bernardino Casas, Chris Bentz, Ramon Ferrer-i-Cancho
Abstract	Entropy is a fundamental property of a repertoire. Here, we present an efficient algorithm to estimate the entropy of types with the help of Zhang’s estimator. The algorithm takes advantage of the fact that the number of different frequencies in a text is in general much smaller than the number of types. We justify the convenience of the algorithm by means of an analysis of the statistical properties of texts from more than 1000 languages. Our work opens up various possibilities for future research.
Tasks
Published	2017-07-26
URL	http://arxiv.org/abs/1707.08290v1
PDF	http://arxiv.org/pdf/1707.08290v1.pdf
PWC	https://paperswithcode.com/paper/fast-calculation-of-entropy-with-zhangs
Repo
Framework

Confident Multiple Choice Learning


Title	Confident Multiple Choice Learning
Authors	Kimin Lee, Changho Hwang, KyoungSoo Park, Jinwoo Shin
Abstract	Ensemble methods are arguably the most trustworthy techniques for boosting the performance of machine learning models. Popular independent ensembles (IE) relying on naive averaging/voting scheme have been of typical choice for most applications involving deep neural networks, but they do not consider advanced collaboration among ensemble models. In this paper, we propose new ensemble methods specialized for deep neural networks, called confident multiple choice learning (CMCL): it is a variant of multiple choice learning (MCL) via addressing its overconfidence issue.In particular, the proposed major components of CMCL beyond the original MCL scheme are (i) new loss, i.e., confident oracle loss, (ii) new architecture, i.e., feature sharing and (iii) new training method, i.e., stochastic labeling. We demonstrate the effect of CMCL via experiments on the image classification on CIFAR and SVHN, and the foreground-background segmentation on the iCoseg. In particular, CMCL using 5 residual networks provides 14.05% and 6.60% relative reductions in the top-1 error rates from the corresponding IE scheme for the classification task on CIFAR and SVHN, respectively.
Tasks	Image Classification
Published	2017-06-12
URL	http://arxiv.org/abs/1706.03475v2
PDF	http://arxiv.org/pdf/1706.03475v2.pdf
PWC	https://paperswithcode.com/paper/confident-multiple-choice-learning
Repo
Framework

Learning opacity in Stratal Maximum Entropy Grammar


Title	Learning opacity in Stratal Maximum Entropy Grammar
Authors	Aleksei Nazarov, Joe Pater
Abstract	Opaque phonological patterns are sometimes claimed to be difficult to learn; specific hypotheses have been advanced about the relative difficulty of particular kinds of opaque processes (Kiparsky 1971, 1973), and the kind of data that will be helpful in learning an opaque pattern (Kiparsky 2000). In this paper, we present a computationally implemented learning theory for one grammatical theory of opacity: a Maximum Entropy version of Stratal OT (Berm'udez-Otero 1999, Kiparsky 2000), and test it on simplified versions of opaque French tense-lax vowel alternations and the opaque interaction of diphthong raising and flapping in Canadian English. We find that the difficulty of opacity can be influenced by evidence for stratal affiliation: the Canadian English case is easier if the learner encounters application of raising outside the flapping context, or non-application of raising between words (i.e., with a raised vowel; with a non-raised vowel).
Tasks
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02517v1
PDF	http://arxiv.org/pdf/1703.02517v1.pdf
PWC	https://paperswithcode.com/paper/learning-opacity-in-stratal-maximum-entropy
Repo
Framework

Synapse at CAp 2017 NER challenge: Fasttext CRF


Title	Synapse at CAp 2017 NER challenge: Fasttext CRF
Authors	Damien Sileo, Camille Pradel, Philippe Muller, Tim Van de Cruys
Abstract	We present our system for the CAp 2017 NER challenge which is about named entity recognition on French tweets. Our system leverages unsupervised learning on a larger dataset of French tweets to learn features feeding a CRF model. It was ranked first without using any gazetteer or structured external data, with an F-measure of 58.89%. To the best of our knowledge, it is the first system to use fasttext embeddings (which include subword representations) and an embedding-based sentence representation for NER.
Tasks	Named Entity Recognition
Published	2017-09-14
URL	http://arxiv.org/abs/1709.04820v1
PDF	http://arxiv.org/pdf/1709.04820v1.pdf
PWC	https://paperswithcode.com/paper/synapse-at-cap-2017-ner-challenge-fasttext
Repo
Framework

Dataset Augmentation with Synthetic Images Improves Semantic Segmentation


Title	Dataset Augmentation with Synthetic Images Improves Semantic Segmentation
Authors	Manik Goyal, Param Rajpura, Hristo Bojinov, Ravi Hegde
Abstract	Although Deep Convolutional Neural Networks trained with strong pixel-level annotations have significantly pushed the performance in semantic segmentation, annotation efforts required for the creation of training data remains a roadblock for further improvements. We show that augmentation of the weakly annotated training dataset with synthetic images minimizes both the annotation efforts and also the cost of capturing images with sufficient variety. Evaluation on the PASCAL 2012 validation dataset shows an increase in mean IOU from 52.80% to 55.47% by adding just 100 synthetic images per object class. Our approach is thus a promising solution to the problems of annotation and dataset collection.
Tasks	Semantic Segmentation
Published	2017-09-04
URL	http://arxiv.org/abs/1709.00849v3
PDF	http://arxiv.org/pdf/1709.00849v3.pdf
PWC	https://paperswithcode.com/paper/dataset-augmentation-with-synthetic-images
Repo
Framework

Approximate Supermodularity Bounds for Experimental Design


Title	Approximate Supermodularity Bounds for Experimental Design
Authors	Luiz F. O. Chamon, Alejandro Ribeiro
Abstract	This work provides performance guarantees for the greedy solution of experimental design problems. In particular, it focuses on A- and E-optimal designs, for which typical guarantees do not apply since the mean-square error and the maximum eigenvalue of the estimation error covariance matrix are not supermodular. To do so, it leverages the concept of approximate supermodularity to derive non-asymptotic worst-case suboptimality bounds for these greedy solutions. These bounds reveal that as the SNR of the experiments decreases, these cost functions behave increasingly as supermodular functions. As such, greedy A- and E-optimal designs approach (1-1/e)-optimality. These results reconcile the empirical success of greedy experimental design with the non-supermodularity of the A- and E-optimality criteria.
Tasks
Published	2017-11-04
URL	http://arxiv.org/abs/1711.01501v2
PDF	http://arxiv.org/pdf/1711.01501v2.pdf
PWC	https://paperswithcode.com/paper/approximate-supermodularity-bounds-for
Repo
Framework

Diversity of preferences can increase collective welfare in sequential exploration problems


Title	Diversity of preferences can increase collective welfare in sequential exploration problems
Authors	Pantelis P. Analytis, Hrvoje Stojic, Alexandros Gelastopoulos, Mehdi Moussaïd
Abstract	In search engines, online marketplaces and other human-computer interfaces large collectives of individuals sequentially interact with numerous alternatives of varying quality. In these contexts, trial and error (exploration) is crucial for uncovering novel high-quality items or solutions, but entails a high cost for individual users. Self-interested decision makers, are often better off imitating the choices of individuals who have already incurred the costs of exploration. Although imitation makes sense at the individual level, it deprives the group of additional information that could have been gleaned by individual explorers. In this paper we show that in such problems, preference diversity can function as a welfare enhancing mechanism. It leads to a consistent increase in the quality of the consumed alternatives that outweighs the increased cost of search for the users.
Tasks
Published	2017-03-28
URL	http://arxiv.org/abs/1703.10970v2
PDF	http://arxiv.org/pdf/1703.10970v2.pdf
PWC	https://paperswithcode.com/paper/diversity-of-preferences-can-increase
Repo
Framework

A Gaussian mixture model representation of endmember variability in hyperspectral unmixing


Title	A Gaussian mixture model representation of endmember variability in hyperspectral unmixing
Authors	Yuan Zhou, Anand Rangarajan, Paul D. Gader
Abstract	Hyperspectral unmixing while considering endmember variability is usually performed by the normal compositional model (NCM), where the endmembers for each pixel are assumed to be sampled from unimodal Gaussian distributions. However, in real applications, the distribution of a material is often not Gaussian. In this paper, we use Gaussian mixture models (GMM) to represent the endmember variability. We show, given the GMM starting premise, that the distribution of the mixed pixel (under the linear mixing model) is also a GMM (and this is shown from two perspectives). The first perspective originates from the random variable transformation and gives a conditional density function of the pixels given the abundances and GMM parameters. With proper smoothness and sparsity prior constraints on the abundances, the conditional density function leads to a standard maximum a posteriori (MAP) problem which can be solved using generalized expectation maximization. The second perspective originates from marginalizing over the endmembers in the GMM, which provides us with a foundation to solve for the endmembers at each pixel. Hence, our model can not only estimate the abundances and distribution parameters, but also the distinct endmember set for each pixel. We tested the proposed GMM on several synthetic and real datasets, and showed its potential by comparing it to current popular methods.
Tasks	Hyperspectral Unmixing
Published	2017-09-29
URL	http://arxiv.org/abs/1710.00075v2
PDF	http://arxiv.org/pdf/1710.00075v2.pdf
PWC	https://paperswithcode.com/paper/a-gaussian-mixture-model-representation-of
Repo
Framework

Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals


Title	Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals
Authors	Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, Xiaogang Wang
Abstract	Vehicle re-identification is an important problem and has many applications in video surveillance and intelligent transportation. It gains increasing attention because of the recent advances of person re-identification techniques. However, unlike person re-identification, the visual differences between pairs of vehicle images are usually subtle and even challenging for humans to distinguish. Incorporating additional spatio-temporal information is vital for solving the challenging re-identification task. Existing vehicle re-identification methods ignored or used over-simplified models for the spatio-temporal relations between vehicle images. In this paper, we propose a two-stage framework that incorporates complex spatio-temporal information for effectively regularizing the re-identification results. Given a pair of vehicle images with their spatio-temporal information, a candidate visual-spatio-temporal path is first generated by a chain MRF model with a deeply learned potential function, where each visual-spatio-temporal state corresponds to an actual vehicle image with its spatio-temporal information. A Siamese-CNN+Path-LSTM model takes the candidate path as well as the pairwise queries to generate their similarity score. Extensive experiments and analysis show the effectiveness of our proposed method and individual components.
Tasks	Person Re-Identification, Vehicle Re-Identification
Published	2017-08-13
URL	http://arxiv.org/abs/1708.03918v1
PDF	http://arxiv.org/pdf/1708.03918v1.pdf
PWC	https://paperswithcode.com/paper/learning-deep-neural-networks-for-vehicle-re
Repo
Framework

Deep Generative Models for Relational Data with Side Information


Title	Deep Generative Models for Relational Data with Side Information
Authors	Changwei Hu, Piyush Rai, Lawrence Carin
Abstract	We present a probabilistic framework for overlapping community discovery and link prediction for relational data, given as a graph. The proposed framework has: (1) a deep architecture which enables us to infer multiple layers of latent features/communities for each node, providing superior link prediction performance on more complex networks and better interpretability of the latent features; and (2) a regression model which allows directly conditioning the node latent features on the side information available in form of node attributes. Our framework handles both (1) and (2) via a clean, unified model, which enjoys full local conjugacy via data augmentation, and facilitates efficient inference via closed form Gibbs sampling. Moreover, inference cost scales in the number of edges which is attractive for massive but sparse networks. Our framework is also easily extendable to model weighted networks with count-valued edges. We compare with various state-of-the-art methods and report results, both quantitative and qualitative, on several benchmark data sets.
Tasks	Data Augmentation, Link Prediction
Published	2017-06-16
URL	http://arxiv.org/abs/1706.05136v1
PDF	http://arxiv.org/pdf/1706.05136v1.pdf
PWC	https://paperswithcode.com/paper/deep-generative-models-for-relational-data
Repo
Framework