July 28, 2019

2933 words 14 mins read

Paper Group ANR 411

Structural Connectome Validation Using Pairwise Classification. An a Priori Exponential Tail Bound for k-Folds Cross-Validation. Comparison of the Deep-Learning-Based Automated Segmentation Methods for the Head Sectioned Images of the Virtual Korean Human Project. Causal Discovery in the Presence of Measurement Error: Identifiability Conditions. Bi …

Structural Connectome Validation Using Pairwise Classification


Title	Structural Connectome Validation Using Pairwise Classification
Authors	Dmitry Petrov, Boris Gutman, Alexander Ivanov, Joshua Faskowitz, Neda Jahanshad, Mikhail Belyaev, Paul Thompson
Abstract	In this work, we study the extent to which structural connectomes and topological derivative measures are unique to individual changes within human brains. To do so, we classify structural connectome pairs from two large longitudinal datasets as either belonging to the same individual or not. Our data is comprised of 227 individuals from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and 226 from the Parkinson’s Progression Markers Initiative (PPMI). We achieve 0.99 area under the ROC curve score for features which represent either weights or network structure of the connectomes (node degrees, PageRank and local efficiency). Our approach may be useful for eliminating noisy features as a preprocessing step in brain aging studies and early diagnosis classification problems.
Tasks
Published	2017-01-26
URL	http://arxiv.org/abs/1701.07847v2
PDF	http://arxiv.org/pdf/1701.07847v2.pdf
PWC	https://paperswithcode.com/paper/structural-connectome-validation-using
Repo
Framework

An a Priori Exponential Tail Bound for k-Folds Cross-Validation


Title	An a Priori Exponential Tail Bound for k-Folds Cross-Validation
Authors	Karim Abou-Moustafa, Csaba Szepesvari
Abstract	We consider a priori generalization bounds developed in terms of cross-validation estimates and the stability of learners. In particular, we first derive an exponential Efron-Stein type tail inequality for the concentration of a general function of n independent random variables. Next, under some reasonable notion of stability, we use this exponential tail bound to analyze the concentration of the k-fold cross-validation (KFCV) estimate around the true risk of a hypothesis generated by a general learning rule. While the accumulated literature has often attributed this concentration to the bias and variance of the estimator, our bound attributes this concentration to the stability of the learning rule and the number of folds k. This insight raises valid concerns related to the practical use of KFCV and suggests research directions to obtain reliable empirical estimates of the actual risk.
Tasks
Published	2017-06-19
URL	http://arxiv.org/abs/1706.05801v1
PDF	http://arxiv.org/pdf/1706.05801v1.pdf
PWC	https://paperswithcode.com/paper/an-a-priori-exponential-tail-bound-for-k
Repo
Framework

Comparison of the Deep-Learning-Based Automated Segmentation Methods for the Head Sectioned Images of the Virtual Korean Human Project


Title	Comparison of the Deep-Learning-Based Automated Segmentation Methods for the Head Sectioned Images of the Virtual Korean Human Project
Authors	Mohammad Eshghi, Holger R. Roth, Masahiro Oda, Min Suk Chung, Kensaku Mori
Abstract	This paper presents an end-to-end pixelwise fully automated segmentation of the head sectioned images of the Visible Korean Human (VKH) project based on Deep Convolutional Neural Networks (DCNNs). By converting classification networks into Fully Convolutional Networks (FCNs), a coarse prediction map, with smaller size than the original input image, can be created for segmentation purposes. To refine this map and to obtain a dense pixel-wise output, standard FCNs use deconvolution layers to upsample the coarse map. However, upsampling based on deconvolution increases the number of network parameters and causes loss of detail because of interpolation. On the other hand, dilated convolution is a new technique introduced recently that attempts to capture multi-scale contextual information without increasing the network parameters while keeping the resolution of the prediction maps high. We used both a standard FCN and a dilated convolution based FCN for semantic segmentation of the head sectioned images of the VKH dataset. Quantitative results showed approximately 20% improvement in the segmentation accuracy when using FCNs with dilated convolutions.
Tasks	Semantic Segmentation
Published	2017-03-15
URL	http://arxiv.org/abs/1703.04967v1
PDF	http://arxiv.org/pdf/1703.04967v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-the-deep-learning-based
Repo
Framework

Causal Discovery in the Presence of Measurement Error: Identifiability Conditions


Title	Causal Discovery in the Presence of Measurement Error: Identifiability Conditions
Authors	Kun Zhang, Mingming Gong, Joseph Ramsey, Kayhan Batmanghelich, Peter Spirtes, Clark Glymour
Abstract	Measurement error in the observed values of the variables can greatly change the output of various causal discovery methods. This problem has received much attention in multiple fields, but it is not clear to what extent the causal model for the measurement-error-free variables can be identified in the presence of measurement error with unknown variance. In this paper, we study precise sufficient identifiability conditions for the measurement-error-free causal model and show what information of the causal model can be recovered from observed data. In particular, we present two different sets of identifiability conditions, based on the second-order statistics and higher-order statistics of the data, respectively. The former was inspired by the relationship between the generating model of the measurement-error-contaminated data and the factor analysis model, and the latter makes use of the identifiability result of the over-complete independent component analysis problem.
Tasks	Causal Discovery
Published	2017-06-10
URL	http://arxiv.org/abs/1706.03768v1
PDF	http://arxiv.org/pdf/1706.03768v1.pdf
PWC	https://paperswithcode.com/paper/causal-discovery-in-the-presence-of
Repo
Framework

Bioplausible multiscale filtering in retino-cortical processing as a mechanism in perceptual grouping


Title	Bioplausible multiscale filtering in retino-cortical processing as a mechanism in perceptual grouping
Authors	Nasim Nematzadeh, David M. W. Powers, Trent W. Lewis
Abstract	Why does our visual system fail to reconstruct reality, when we look at certain patterns? Where do Geometrical illusions start to emerge in the visual pathway? How far should we take computational models of vision with the same visual ability to detect illusions as we do? This study addresses these questions, by focusing on a specific underlying neural mechanism involved in our visual experiences that affects our final perception. Among many types of visual illusion, Geometrical and, in particular, Tilt Illusions are rather important, being characterized by misperception of geometric patterns involving lines and tiles in combination with contrasting orientation, size or position. Over the last decade, many new neurophysiological experiments have led to new insights as to how, when and where retinal processing takes place, and the encoding nature of the retinal representation that is sent to the cortex for further processing. Based on these neurobiological discoveries, we provide computer simulation evidence from modelling retinal ganglion cells responses to some complex Tilt Illusions, suggesting that the emergence of tilt in these illusions is partially related to the interaction of multiscale visual processing performed in the retina. The output of our low-level filtering model is presented for several types of Tilt Illusion, predicting that the final tilt percept arises from multiple-scale processing of the Differences of Gaussians and the perceptual interaction of foreground and background elements. Our results suggest that this model has a high potential in revealing the underlying mechanism connecting low-level filtering approaches to mid- and high-level explanations such as Anchoring theory and Perceptual grouping.
Tasks
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08115v3
PDF	http://arxiv.org/pdf/1702.08115v3.pdf
PWC	https://paperswithcode.com/paper/bioplausible-multiscale-filtering-in-retino
Repo
Framework

Helping News Editors Write Better Headlines: A Recommender to Improve the Keyword Contents & Shareability of News Headlines


Title	Helping News Editors Write Better Headlines: A Recommender to Improve the Keyword Contents & Shareability of News Headlines
Authors	Terrence Szymanski, Claudia Orellana-Rodriguez, Mark T. Keane
Abstract	We present a software tool that employs state-of-the-art natural language processing (NLP) and machine learning techniques to help newspaper editors compose effective headlines for online publication. The system identifies the most salient keywords in a news article and ranks them based on both their overall popularity and their direct relevance to the article. The system also uses a supervised regression model to identify headlines that are likely to be widely shared on social media. The user interface is designed to simplify and speed the editor’s decision process on the composition of the headline. As such, the tool provides an efficient way to combine the benefits of automated predictors of engagement and search-engine optimization (SEO) with human judgments of overall headline quality.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09656v1
PDF	http://arxiv.org/pdf/1705.09656v1.pdf
PWC	https://paperswithcode.com/paper/helping-news-editors-write-better-headlines-a
Repo
Framework

Stochastic Zeroth-order Optimization in High Dimensions


Title	Stochastic Zeroth-order Optimization in High Dimensions
Authors	Yining Wang, Simon Du, Sivaraman Balakrishnan, Aarti Singh
Abstract	We consider the problem of optimizing a high-dimensional convex function using stochastic zeroth-order queries. Under sparsity assumptions on the gradients or function values, we present two algorithms: a successive component/feature selection algorithm and a noisy mirror descent algorithm using Lasso gradient estimates, and show that both algorithms have convergence rates that de- pend only logarithmically on the ambient dimension of the problem. Empirical results confirm our theoretical findings and show that the algorithms we design outperform classical zeroth-order optimization methods in the high-dimensional setting.
Tasks	Feature Selection
Published	2017-10-29
URL	http://arxiv.org/abs/1710.10551v2
PDF	http://arxiv.org/pdf/1710.10551v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-zeroth-order-optimization-in-high
Repo
Framework

Pixel Normalization from Numeric Data as Input to Neural Networks


Title	Pixel Normalization from Numeric Data as Input to Neural Networks
Authors	Parth Sane, Ravindra Agrawal
Abstract	Text to image transformation for input to neural networks requires intermediate steps. This paper attempts to present a new approach to pixel normalization so as to convert textual data into image, suitable as input for neural networks. This method can be further improved by its Graphics Processing Unit (GPU) implementation to provide significant speedup in computational time.
Tasks
Published	2017-05-04
URL	http://arxiv.org/abs/1705.01809v1
PDF	http://arxiv.org/pdf/1705.01809v1.pdf
PWC	https://paperswithcode.com/paper/pixel-normalization-from-numeric-data-as
Repo
Framework

Anveshak - A Groundtruth Generation Tool for Foreground Regions of Document Images


Title	Anveshak - A Groundtruth Generation Tool for Foreground Regions of Document Images
Authors	Soumyadeep Dey, Jayanta Mukherjee, Shamik Sural, Amit Vijay Nandedkar
Abstract	We propose a graphical user interface based groundtruth generation tool in this paper. Here, annotation of an input document image is done based on the foreground pixels. Foreground pixels are grouped together with user interaction to form labeling units. These units are then labeled by the user with the user defined labels. The output produced by the tool is an image with an XML file containing its metadata information. This annotated data can be further used in different applications of document image analysis.
Tasks
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02831v1
PDF	http://arxiv.org/pdf/1708.02831v1.pdf
PWC	https://paperswithcode.com/paper/anveshak-a-groundtruth-generation-tool-for
Repo
Framework

Saving Gradient and Negative Curvature Computations: Finding Local Minima More Efficiently


Title	Saving Gradient and Negative Curvature Computations: Finding Local Minima More Efficiently
Authors	Yaodong Yu, Difan Zou, Quanquan Gu
Abstract	We propose a family of nonconvex optimization algorithms that are able to save gradient and negative curvature computations to a large extent, and are guaranteed to find an approximate local minimum with improved runtime complexity. At the core of our algorithms is the division of the entire domain of the objective function into small and large gradient regions: our algorithms only perform gradient descent based procedure in the large gradient region, and only perform negative curvature descent in the small gradient region. Our novel analysis shows that the proposed algorithms can escape the small gradient region in only one negative curvature descent step whenever they enter it, and thus they only need to perform at most $N_{\epsilon}$ negative curvature direction computations, where $N_{\epsilon}$ is the number of times the algorithms enter small gradient regions. For both deterministic and stochastic settings, we show that the proposed algorithms can potentially beat the state-of-the-art local minima finding algorithms. For the finite-sum setting, our algorithm can also outperform the best algorithm in a certain regime.
Tasks
Published	2017-12-11
URL	http://arxiv.org/abs/1712.03950v1
PDF	http://arxiv.org/pdf/1712.03950v1.pdf
PWC	https://paperswithcode.com/paper/saving-gradient-and-negative-curvature
Repo
Framework

Asymptotic Analysis via Stochastic Differential Equations of Gradient Descent Algorithms in Statistical and Computational Paradigms


Title	Asymptotic Analysis via Stochastic Differential Equations of Gradient Descent Algorithms in Statistical and Computational Paradigms
Authors	Yazhen Wang
Abstract	This paper investigates asymptotic behaviors of gradient descent algorithms (particularly accelerated gradient descent and stochastic gradient descent) in the context of stochastic optimization arising in statistics and machine learning where objective functions are estimated from available data. We show that these algorithms can be computationally modeled by continuous-time ordinary or stochastic differential equations. We establish gradient flow central limit theorems to describe the limiting dynamic behaviors of these computational algorithms and the large-sample performances of the related statistical procedures, as the number of algorithm iterations and data size both go to infinity, where the gradient flow central limit theorems are governed by some linear ordinary or stochastic differential equations like time-dependent Ornstein-Uhlenbeck processes. We illustrate that our study can provide a novel unified framework for a joint computational and statistical asymptotic analysis, where the computational asymptotic analysis studies dynamic behaviors of these algorithms with the time (or the number of iterations in the algorithms), the statistical asymptotic analysis investigates large sample behaviors of the statistical procedures (like estimators and classifiers) that the algorithms are applied to compute, and in fact the statistical procedures are equal to the limits of the random sequences generated from these iterative algorithms as the number of iterations goes to infinity. The joint analysis results based on the obtained gradient flow central limit theorems can identify four factors - learning rate, batch size, gradient covariance, and Hessian - to derive new theory regarding the local minima found by stochastic gradient descent for solving non-convex optimization problems.
Tasks	Stochastic Optimization
Published	2017-11-27
URL	https://arxiv.org/abs/1711.09514v5
PDF	https://arxiv.org/pdf/1711.09514v5.pdf
PWC	https://paperswithcode.com/paper/asymptotic-analysis-via-stochastic
Repo
Framework

Reply With: Proactive Recommendation of Email Attachments


Title	Reply With: Proactive Recommendation of Email Attachments
Authors	Christophe Van Gysel, Bhaskar Mitra, Matteo Venanzi, Roy Rosemarin, Grzegorz Kukla, Piotr Grudzien, Nicola Cancedda
Abstract	Email responses often contain items-such as a file or a hyperlink to an external document-that are attached to or included inline in the body of the message. Analysis of an enterprise email corpus reveals that 35% of the time when users include these items as part of their response, the attachable item is already present in their inbox or sent folder. A modern email client can proactively retrieve relevant attachable items from the user’s past emails based on the context of the current conversation, and recommend them for inclusion, to reduce the time and effort involved in composing the response. In this paper, we propose a weakly supervised learning framework for recommending attachable items to the user. As email search systems are commonly available, we constrain the recommendation task to formulating effective search queries from the context of the conversations. The query is submitted to an existing IR system to retrieve relevant items for attachment. We also present a novel strategy for generating labels from an email corpus—without the need for manual annotations—that can be used to train and evaluate the query formulation model. In addition, we describe a deep convolutional neural network that demonstrates satisfactory performance on this query formulation task when evaluated on the publicly available Avocado dataset and a proprietary dataset of internal emails obtained through an employee participation program.
Tasks
Published	2017-10-17
URL	http://arxiv.org/abs/1710.06061v2
PDF	http://arxiv.org/pdf/1710.06061v2.pdf
PWC	https://paperswithcode.com/paper/reply-with-proactive-recommendation-of-email
Repo
Framework

LatentPoison - Adversarial Attacks On The Latent Space


Title	LatentPoison - Adversarial Attacks On The Latent Space
Authors	Antonia Creswell, Anil A. Bharath, Biswa Sengupta
Abstract	Robustness and security of machine learning (ML) systems are intertwined, wherein a non-robust ML system (classifiers, regressors, etc.) can be subject to attacks using a wide variety of exploits. With the advent of scalable deep learning methodologies, a lot of emphasis has been put on the robustness of supervised, unsupervised and reinforcement learning algorithms. Here, we study the robustness of the latent space of a deep variational autoencoder (dVAE), an unsupervised generative framework, to show that it is indeed possible to perturb the latent space, flip the class predictions and keep the classification probability approximately equal before and after an attack. This means that an agent that looks at the outputs of a decoder would remain oblivious to an attack.
Tasks
Published	2017-11-08
URL	http://arxiv.org/abs/1711.02879v1
PDF	http://arxiv.org/pdf/1711.02879v1.pdf
PWC	https://paperswithcode.com/paper/latentpoison-adversarial-attacks-on-the
Repo
Framework

Ruminating Reader: Reasoning with Gated Multi-Hop Attention


Title	Ruminating Reader: Reasoning with Gated Multi-Hop Attention
Authors	Yichen Gong, Samuel R. Bowman
Abstract	To answer the question in machine comprehension (MC) task, the models need to establish the interaction between the question and the context. To tackle the problem that the single-pass model cannot reflect on and correct its answer, we present Ruminating Reader. Ruminating Reader adds a second pass of attention and a novel information fusion component to the Bi-Directional Attention Flow model (BiDAF). We propose novel layer structures that construct an query-aware context vector representation and fuse encoding representation with intermediate representation on top of BiDAF model. We show that a multi-hop attention mechanism can be applied to a bi-directional attention structure. In experiments on SQuAD, we find that the Reader outperforms the BiDAF baseline by a substantial margin, and matches or surpasses the performance of all other published systems.
Tasks	Question Answering, Reading Comprehension
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07415v1
PDF	http://arxiv.org/pdf/1704.07415v1.pdf
PWC	https://paperswithcode.com/paper/ruminating-reader-reasoning-with-gated-multi
Repo
Framework

A Stylometric Inquiry into Hyperpartisan and Fake News


Title	A Stylometric Inquiry into Hyperpartisan and Fake News
Authors	Martin Potthast, Johannes Kiesel, Kevin Reinartz, Janek Bevendorff, Benno Stein
Abstract	This paper reports on a writing style analysis of hyperpartisan (i.e., extremely one-sided) news in connection to fake news. It presents a large corpus of 1,627 articles that were manually fact-checked by professional journalists from BuzzFeed. The articles originated from 9 well-known political publishers, 3 each from the mainstream, the hyperpartisan left-wing, and the hyperpartisan right-wing. In sum, the corpus contains 299 fake news, 97% of which originated from hyperpartisan publishers. We propose and demonstrate a new way of assessing style similarity between text categories via Unmasking—a meta-learning approach originally devised for authorship verification—, revealing that the style of left-wing and right-wing news have a lot more in common than any of the two have with the mainstream. Furthermore, we show that hyperpartisan news can be discriminated well by its style from the mainstream (F1=0.78), as can be satire from both (F1=0.81). Unsurprisingly, style-based fake news detection does not live up to scratch (F1=0.46). Nevertheless, the former results are important to implement pre-screening for fake news detectors.
Tasks	Fake News Detection, Meta-Learning
Published	2017-02-18
URL	http://arxiv.org/abs/1702.05638v1
PDF	http://arxiv.org/pdf/1702.05638v1.pdf
PWC	https://paperswithcode.com/paper/a-stylometric-inquiry-into-hyperpartisan-and
Repo
Framework