July 28, 2019

3224 words 16 mins read

Paper Group ANR 436

Dimensionality reduction methods for molecular simulations. Multitask Learning using Task Clustering with Applications to Predictive Modeling and GWAS of Plant Varieties. A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates. PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimizat …

Dimensionality reduction methods for molecular simulations


Title	Dimensionality reduction methods for molecular simulations
Authors	Stefan Doerr, Igor Ariz-Extreme, Matthew J. Harvey, Gianni De Fabritiis
Abstract	Molecular simulations produce very high-dimensional data-sets with millions of data points. As analysis methods are often unable to cope with so many dimensions, it is common to use dimensionality reduction and clustering methods to reach a reduced representation of the data. Yet these methods often fail to capture the most important features necessary for the construction of a Markov model. Here we demonstrate the results of various dimensionality reduction methods on two simulation data-sets, one of protein folding and another of protein-ligand binding. The methods tested include a k-means clustering variant, a non-linear auto encoder, principal component analysis and tICA. The dimension-reduced data is then used to estimate the implied timescales of the slowest process by a Markov state model analysis to assess the quality of the projection. The projected dimensions learned from the data are visualized to demonstrate which conformations the various methods choose to represent the molecular process.
Tasks	Dimensionality Reduction
Published	2017-10-29
URL	http://arxiv.org/abs/1710.10629v2
PDF	http://arxiv.org/pdf/1710.10629v2.pdf
PWC	https://paperswithcode.com/paper/dimensionality-reduction-methods-for
Repo
Framework

Multitask Learning using Task Clustering with Applications to Predictive Modeling and GWAS of Plant Varieties


Title	Multitask Learning using Task Clustering with Applications to Predictive Modeling and GWAS of Plant Varieties
Authors	Ming Yu, Addie M. Thompson, Karthikeyan Natesan Ramamurthy, Eunho Yang, Aurélie C. Lozano
Abstract	Inferring predictive maps between multiple input and multiple output variables or tasks has innumerable applications in data science. Multi-task learning attempts to learn the maps to several output tasks simultaneously with information sharing between them. We propose a novel multi-task learning framework for sparse linear regression, where a full task hierarchy is automatically inferred from the data, with the assumption that the task parameters follow a hierarchical tree structure. The leaves of the tree are the parameters for individual tasks, and the root is the global model that approximates all the tasks. We apply the proposed approach to develop and evaluate: (a) predictive models of plant traits using large-scale and automated remote sensing data, and (b) GWAS methodologies mapping such derived phenotypes in lieu of hand-measured traits. We demonstrate the superior performance of our approach compared to other methods, as well as the usefulness of discovering hierarchical groupings between tasks. Our results suggest that richer genetic mapping can indeed be obtained from the remote sensing data. In addition, our discovered groupings reveal interesting insights from a plant science perspective.
Tasks	Multi-Task Learning
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01788v1
PDF	http://arxiv.org/pdf/1710.01788v1.pdf
PWC	https://paperswithcode.com/paper/multitask-learning-using-task-clustering-with
Repo
Framework

A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates


Title	A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates
Authors	Zhi Li, Wei Shi, Ming Yan
Abstract	This paper proposes a novel proximal-gradient algorithm for a decentralized optimization problem with a composite objective containing smooth and non-smooth terms. Specifically, the smooth and nonsmooth terms are dealt with by gradient and proximal updates, respectively. The proposed algorithm is closely related to a previous algorithm, PG-EXTRA \cite{shi2015proximal}, but has a few advantages. First of all, agents use uncoordinated step-sizes, and the stable upper bounds on step-sizes are independent of network topologies. The step-sizes depend on local objective functions, and they can be as large as those of the gradient descent. Secondly, for the special case without non-smooth terms, linear convergence can be achieved under the strong convexity assumption. The dependence of the convergence rate on the objective functions and the network are separated, and the convergence rate of the new algorithm is as good as one of the two convergence rates that match the typical rates for the general gradient descent and the consensus averaging. We provide numerical experiments to demonstrate the efficacy of the introduced algorithm and validate our theoretical discoveries.
Tasks
Published	2017-04-25
URL	https://arxiv.org/abs/1704.07807v2
PDF	https://arxiv.org/pdf/1704.07807v2.pdf
PWC	https://paperswithcode.com/paper/a-decentralized-proximal-gradient-method-with
Repo
Framework

PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization


Title	PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization
Authors	Ye Tian, Ran Cheng, Xingyi Zhang, Yaochu Jin
Abstract	Over the last three decades, a large number of evolutionary algorithms have been developed for solving multiobjective optimization problems. However, there lacks an up-to-date and comprehensive software platform for researchers to properly benchmark existing algorithms and for practitioners to apply selected algorithms to solve their real-world problems. The demand of such a common tool becomes even more urgent, when the source code of many proposed algorithms has not been made publicly available. To address these issues, we have developed a MATLAB platform for evolutionary multi-objective optimization in this paper, called PlatEMO, which includes more than 50 multi-objective evolutionary algorithms and more than 100 multi-objective test problems, along with several widely used performance indicators. With a user-friendly graphical user interface, PlatEMO enables users to easily compare several evolutionary algorithms at one time and collect statistical results in Excel or LaTeX files. More importantly, PlatEMO is completely open source, such that users are able to develop new algorithms on the basis of it. This paper introduces the main features of PlatEMO and illustrates how to use it for performing comparative experiments, embedding new algorithms, creating new test problems, and developing performance indicators. Source code of PlatEMO is now available at: http://bimk.ahu.edu.cn/index.php?s=/Index/Software/index.html.
Tasks	Multiobjective Optimization
Published	2017-01-04
URL	http://arxiv.org/abs/1701.00879v1
PDF	http://arxiv.org/pdf/1701.00879v1.pdf
PWC	https://paperswithcode.com/paper/platemo-a-matlab-platform-for-evolutionary
Repo
Framework

DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution


Title	DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution
Authors	Thomas Vandal, Evan Kodra, Sangram Ganguly, Andrew Michaelis, Ramakrishna Nemani, Auroop R Ganguly
Abstract	The impacts of climate change are felt by most critical systems, such as infrastructure, ecological systems, and power-plants. However, contemporary Earth System Models (ESM) are run at spatial resolutions too coarse for assessing effects this localized. Local scale projections can be obtained using statistical downscaling, a technique which uses historical climate observations to learn a low-resolution to high-resolution mapping. Depending on statistical modeling choices, downscaled projections have been shown to vary significantly terms of accuracy and reliability. The spatio-temporal nature of the climate system motivates the adaptation of super-resolution image processing techniques to statistical downscaling. In our work, we present DeepSD, a generalized stacked super resolution convolutional neural network (SRCNN) framework for statistical downscaling of climate variables. DeepSD augments SRCNN with multi-scale input channels to maximize predictability in statistical downscaling. We provide a comparison with Bias Correction Spatial Disaggregation as well as three Automated-Statistical Downscaling approaches in downscaling daily precipitation from 1 degree (~100km) to 1/8 degrees (~12.5km) over the Continental United States. Furthermore, a framework using the NASA Earth Exchange (NEX) platform is discussed for downscaling more than 20 ESM models with multiple emission scenarios.
Tasks	Image Super-Resolution, Super-Resolution
Published	2017-03-09
URL	http://arxiv.org/abs/1703.03126v1
PDF	http://arxiv.org/pdf/1703.03126v1.pdf
PWC	https://paperswithcode.com/paper/deepsd-generating-high-resolution-climate
Repo
Framework

Learning What Data to Learn


Title	Learning What Data to Learn
Authors	Yang Fan, Fei Tian, Tao Qin, Jiang Bian, Tie-Yan Liu
Abstract	Machine learning is essentially the sciences of playing with data. An adaptive data selection strategy, enabling to dynamically choose different data at various training stages, can reach a more effective model in a more efficient way. In this paper, we propose a deep reinforcement learning framework, which we call \emph{\textbf{N}eural \textbf{D}ata \textbf{F}ilter} (\textbf{NDF}), to explore automatic and adaptive data selection in the training process. In particular, NDF takes advantage of a deep neural network to adaptively select and filter important data instances from a sequential stream of training data, such that the future accumulative reward (e.g., the convergence speed) is maximized. In contrast to previous studies in data selection that is mainly based on heuristic strategies, NDF is quite generic and thus can be widely suitable for many machine learning tasks. Taking neural network training with stochastic gradient descent (SGD) as an example, comprehensive experiments with respect to various neural network modeling (e.g., multi-layer perceptron networks, convolutional neural networks and recurrent neural networks) and several applications (e.g., image classification and text understanding) demonstrate that NDF powered SGD can achieve comparable accuracy with standard SGD process by using less data and fewer iterations.
Tasks	Image Classification
Published	2017-02-28
URL	http://arxiv.org/abs/1702.08635v1
PDF	http://arxiv.org/pdf/1702.08635v1.pdf
PWC	https://paperswithcode.com/paper/learning-what-data-to-learn
Repo
Framework

Classification of Questions and Learning Outcome Statements (LOS) Into Blooms Taxonomy (BT) By Similarity Measurements Towards Extracting Of Learning Outcome from Learning Material


Title	Classification of Questions and Learning Outcome Statements (LOS) Into Blooms Taxonomy (BT) By Similarity Measurements Towards Extracting Of Learning Outcome from Learning Material
Authors	Shadi Diab, Badie Sartawi
Abstract	Blooms Taxonomy (BT) have been used to classify the objectives of learning outcome by dividing the learning into three different domains; the cognitive domain, the effective domain and the psychomotor domain. In this paper, we are introducing a new approach to classify the questions and learning outcome statements (LOS) into Blooms taxonomy (BT) and to verify BT verb lists, which are being cited and used by academicians to write questions and (LOS). An experiment was designed to investigate the semantic relationship between the action verbs used in both questions and LOS to obtain more accurate classification of the levels of BT. A sample of 775 different action verbs collected from different universities allows us to measure an accurate and clear-cut cognitive level for the action verb. It is worth mentioning that natural language processing techniques were used to develop our rules as to induce the questions into chunks in order to extract the action verbs. Our proposed solution was able to classify the action verb into a precise level of the cognitive domain. We, on our side, have tested and evaluated our proposed solution using confusion matrix. The results of evaluation tests yielded 97% for the macro average of precision and 90% for F1. Thus, the outcome of the research suggests that it is crucial to analyse and verify the action verbs cited and used by academicians to write LOS and classify their questions based on blooms taxonomy in order to obtain a definite and more accurate classification.
Tasks
Published	2017-06-10
URL	http://arxiv.org/abs/1706.03191v2
PDF	http://arxiv.org/pdf/1706.03191v2.pdf
PWC	https://paperswithcode.com/paper/classification-of-questions-and-learning
Repo
Framework

An online sequence-to-sequence model for noisy speech recognition


Title	An online sequence-to-sequence model for noisy speech recognition
Authors	Chung-Cheng Chiu, Dieterich Lawson, Yuping Luo, George Tucker, Kevin Swersky, Ilya Sutskever, Navdeep Jaitly
Abstract	Generative models have long been the dominant approach for speech recognition. The success of these models however relies on the use of sophisticated recipes and complicated machinery that is not easily accessible to non-practitioners. Recent innovations in Deep Learning have given rise to an alternative - discriminative models called Sequence-to-Sequence models, that can almost match the accuracy of state of the art generative models. While these models are easy to train as they can be trained end-to-end in a single step, they have a practical limitation that they can only be used for offline recognition. This is because the models require that the entirety of the input sequence be available at the beginning of inference, an assumption that is not valid for instantaneous speech recognition. To address this problem, online sequence-to-sequence models were recently introduced. These models are able to start producing outputs as data arrives, and the model feels confident enough to output partial transcripts. These models, like sequence-to-sequence are causal - the output produced by the model until any time, $t$, affects the features that are computed subsequently. This makes the model inherently more powerful than generative models that are unable to change features that are computed from the data. This paper highlights two main contributions - an improvement to online sequence-to-sequence model training, and its application to noisy settings with mixed speech from two speakers.
Tasks	Noisy Speech Recognition, Speech Recognition
Published	2017-06-16
URL	http://arxiv.org/abs/1706.06428v1
PDF	http://arxiv.org/pdf/1706.06428v1.pdf
PWC	https://paperswithcode.com/paper/an-online-sequence-to-sequence-model-for
Repo
Framework

Optimizing for Measure of Performance in Max-Margin Parsing


Title	Optimizing for Measure of Performance in Max-Margin Parsing
Authors	Alexander Bauer, Shinichi Nakajima, Nico Görnitz, Klaus-Robert Müller
Abstract	Many statistical learning problems in the area of natural language processing including sequence tagging, sequence segmentation and syntactic parsing has been successfully approached by means of structured prediction methods. An appealing property of the corresponding discriminative learning algorithms is their ability to integrate the loss function of interest directly into the optimization process, which potentially can increase the resulting performance accuracy. Here, we demonstrate on the example of constituency parsing how to optimize for F1-score in the max-margin framework of structural SVM. In particular, the optimization is with respect to the original (not binarized) trees.
Tasks	Constituency Parsing, Structured Prediction
Published	2017-09-05
URL	http://arxiv.org/abs/1709.01562v2
PDF	http://arxiv.org/pdf/1709.01562v2.pdf
PWC	https://paperswithcode.com/paper/optimizing-for-measure-of-performance-in-max
Repo
Framework

Question Analysis for Arabic Question Answering Systems


Title	Question Analysis for Arabic Question Answering Systems
Authors	Waheeb Ahmed, Dr. Anto P Babu
Abstract	The first step of processing a question in Question Answering(QA) Systems is to carry out a detailed analysis of the question for the purpose of determining what it is asking for and how to perfectly approach answering it. Our Question analysis uses several techniques to analyze any question given in natural language: a Stanford POS Tagger & parser for Arabic language, a named entity recognizer, tokenizer,Stop-word removal, Question expansion, Question classification and Question focus extraction components. We employ numerous detection rules and trained classifier using features from this analysis to detect important elements of the question, including: 1) the portion of the question that is a referring to the answer (the focus); 2) different terms in the question that identify what type of entity is being asked for (the lexical answer types); 3) Question expansion ; 4) a process of classifying the question into one or more of several and different types; and We describe how these elements are identified and evaluate the effect of accurate detection on our question-answering system using the Mean Reciprocal Rank(MRR) accuracy measure.
Tasks	Question Answering
Published	2017-01-11
URL	http://arxiv.org/abs/1701.02925v1
PDF	http://arxiv.org/pdf/1701.02925v1.pdf
PWC	https://paperswithcode.com/paper/question-analysis-for-arabic-question
Repo
Framework

Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing


Title	Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing
Authors	Xu Sun, Weiwei Sun, Shuming Ma, Xuancheng Ren, Yi Zhang, Wenjie Li, Houfeng Wang
Abstract	Recent systems on structured prediction focus on increasing the level of structural dependencies within the model. However, our study suggests that complex structures entail high overfitting risks. To control the structure-based overfitting, we propose to conduct structure regularization decoding (SR decoding). The decoding of the complex structure model is regularized by the additionally trained simple structure model. We theoretically analyze the quantitative relations between the structural complexity and the overfitting risk. The analysis shows that complex structure models are prone to the structure-based overfitting. Empirical evaluations show that the proposed method improves the performance of the complex structure models by reducing the structure-based overfitting. On the sequence labeling tasks, the proposed method substantially improves the performance of the complex neural network models. The maximum F1 error rate reduction is 36.4% for the third-order model. The proposed method also works for the parsing task. The maximum UAS improvement is 5.5% for the tri-sibling model. The results are competitive with or better than the state-of-the-art results.
Tasks	Structured Prediction
Published	2017-11-25
URL	http://arxiv.org/abs/1711.10331v1
PDF	http://arxiv.org/pdf/1711.10331v1.pdf
PWC	https://paperswithcode.com/paper/complex-structure-leads-to-overfitting-a
Repo
Framework

Depth estimation using structured light flow – analysis of projected pattern flow on an object’s surface –


Title	Depth estimation using structured light flow – analysis of projected pattern flow on an object’s surface –
Authors	Ryo Furukawa, Ryusuke Sagawa, Hiroshi Kawasaki
Abstract	Shape reconstruction techniques using structured light have been widely researched and developed due to their robustness, high precision, and density. Because the techniques are based on decoding a pattern to find correspondences, it implicitly requires that the projected patterns be clearly captured by an image sensor, i.e., to avoid defocus and motion blur of the projected pattern. Although intensive researches have been conducted for solving defocus blur, few researches for motion blur and only solution is to capture with extremely fast shutter speed. In this paper, unlike the previous approaches, we actively utilize motion blur, which we refer to as a light flow, to estimate depth. Analysis reveals that minimum two light flows, which are retrieved from two projected patterns on the object, are required for depth estimation. To retrieve two light flows at the same time, two sets of parallel line patterns are illuminated from two video projectors and the size of motion blur of each line is precisely measured. By analyzing the light flows, i.e. lengths of the blurs, scene depth information is estimated. In the experiments, 3D shapes of fast moving objects, which are inevitably captured with motion blur, are successfully reconstructed by our technique.
Tasks	Depth Estimation
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00513v1
PDF	http://arxiv.org/pdf/1710.00513v1.pdf
PWC	https://paperswithcode.com/paper/depth-estimation-using-structured-light-flow
Repo
Framework

Probabilistic Diffeomorphic Registration: Representing Uncertainty


Title	Probabilistic Diffeomorphic Registration: Representing Uncertainty
Authors	Demian Wassermann, Matt Toews, Marc Niethammer, William Wells Iii
Abstract	This paper presents a novel mathematical framework for representing uncertainty in large deformation diffeomorphic image registration. The Bayesian posterior distribution over the deformations aligning a moving and a fixed image is approximated via a variational formulation. A stochastic differential equation (SDE) modeling the deformations as the evolution of a time-varying velocity field leads to a prior density over deformations in the form of a Gaussian process. This permits estimating the full posterior distribution in order to represent uncertainty, in contrast to methods in which the posterior is approximated via Monte Carlo sampling or maximized in maximum a-posteriori (MAP) estimation. The frame-work is demonstrated in the case of landmark-based image registration, including simulated data and annotated pre and intra-operative 3D images.
Tasks	Image Registration
Published	2017-01-12
URL	http://arxiv.org/abs/1701.03266v1
PDF	http://arxiv.org/pdf/1701.03266v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-diffeomorphic-registration
Repo
Framework

How far did we get in face spoofing detection?


Title	How far did we get in face spoofing detection?
Authors	Luiz Souza, Mauricio Pamplona, Luciano Oliveira, João Papa
Abstract	The growing use of control access systems based on face recognition shed light over the need for even more accurate systems to detect face spoofing attacks. In this paper, an extensive analysis on face spoofing detection works published in the last decade is presented. The analyzed works are categorized by their fundamental parts, i.e., descriptors and classifiers. This structured survey also brings the temporal evolution of the face spoofing detection field, as well as a comparative analysis of the works considering the most important public data sets in the field. The methodology followed in this work is particularly relevant to observe trends in the existing approaches, to discuss still opened issues, and to propose new perspectives for the future of face spoofing detection.
Tasks	Face Recognition
Published	2017-10-26
URL	http://arxiv.org/abs/1710.09868v2
PDF	http://arxiv.org/pdf/1710.09868v2.pdf
PWC	https://paperswithcode.com/paper/how-far-did-we-get-in-face-spoofing-detection
Repo
Framework

Unifying DAGs and UGs


Title	Unifying DAGs and UGs
Authors	Jose M. Peña
Abstract	We introduce a new class of graphical models that generalizes Lauritzen-Wermuth-Frydenberg chain graphs by relaxing the semi-directed acyclity constraint so that only directed cycles are forbidden. Moreover, up to two edges are allowed between any pair of nodes. Specifically, we present local, pairwise and global Markov properties for the new graphical models and prove their equivalence. We also present an equivalent factorization property. Finally, we present a causal interpretation of the new models.
Tasks
Published	2017-08-29
URL	http://arxiv.org/abs/1708.08722v8
PDF	http://arxiv.org/pdf/1708.08722v8.pdf
PWC	https://paperswithcode.com/paper/unifying-dags-and-ugs
Repo
Framework