July 27, 2019

2958 words 14 mins read

Paper Group ANR 589

Convex Optimization with Unbounded Nonconvex Oracles using Simulated Annealing. Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model. SIMLR: A Tool for Large-Scale Genomic Analyses by Multi-Kernel Learning. ClustGeo: an R package for hierarchical clustering with spatial constraints. Cultivating DNN Diversity for Large Scale Vid …

Convex Optimization with Unbounded Nonconvex Oracles using Simulated Annealing


Title	Convex Optimization with Unbounded Nonconvex Oracles using Simulated Annealing
Authors	Oren Mangoubi, Nisheeth K. Vishnoi
Abstract	We consider the problem of minimizing a convex objective function $F$ when one can only evaluate its noisy approximation $\hat{F}$. Unless one assumes some structure on the noise, $\hat{F}$ may be an arbitrary nonconvex function, making the task of minimizing $F$ intractable. To overcome this, prior work has often focused on the case when $F(x)-\hat{F}(x)$ is uniformly-bounded. In this paper we study the more general case when the noise has magnitude $\alpha F(x) + \beta$ for some $\alpha, \beta > 0$, and present a polynomial time algorithm that finds an approximate minimizer of $F$ for this noise model. Previously, Markov chains, such as the stochastic gradient Langevin dynamics, have been used to arrive at approximate solutions to these optimization problems. However, for the noise model considered in this paper, no single temperature allows such a Markov chain to both mix quickly and concentrate near the global minimizer. We bypass this by combining “simulated annealing” with the stochastic gradient Langevin dynamics, and gradually decreasing the temperature of the chain in order to approach the global minimizer. As a corollary one can approximately minimize a nonconvex function that is close to a convex function; however, the closeness can deteriorate as one moves away from the optimum.
Tasks
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02621v2
PDF	http://arxiv.org/pdf/1711.02621v2.pdf
PWC	https://paperswithcode.com/paper/convex-optimization-with-unbounded-nonconvex
Repo
Framework

Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model


Title	Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model
Authors	M. Saquib Sarfraz, Arne Schumann, Yan Wang, Rainer Stiefelhagen
Abstract	Pedestrian attribute inference is a demanding problem in visual surveillance that can facilitate person retrieval, search and indexing. To exploit semantic relations between attributes, recent research treats it as a multi-label image classification task. The visual cues hinting at attributes can be strongly localized and inference of person attributes such as hair, backpack, shorts, etc., are highly dependent on the acquired view of the pedestrian. In this paper we assert this dependence in an end-to-end learning framework and show that a view-sensitive attribute inference is able to learn better attribute predictions. Our proposed model jointly predicts the coarse pose (view) of the pedestrian and learns specialized view-specific multi-label attribute predictions. We show in an extensive evaluation on three challenging datasets (PETA, RAP and WIDER) that our proposed end-to-end view-aware attribute prediction model provides competitive performance and improves on the published state-of-the-art on these datasets.
Tasks	Image Classification, Person Retrieval
Published	2017-07-19
URL	http://arxiv.org/abs/1707.06089v1
PDF	http://arxiv.org/pdf/1707.06089v1.pdf
PWC	https://paperswithcode.com/paper/deep-view-sensitive-pedestrian-attribute
Repo
Framework

SIMLR: A Tool for Large-Scale Genomic Analyses by Multi-Kernel Learning


Title	SIMLR: A Tool for Large-Scale Genomic Analyses by Multi-Kernel Learning
Authors	Bo Wang, Daniele Ramazzotti, Luca De Sano, Junjie Zhu, Emma Pierson, Serafim Batzoglou
Abstract	We here present SIMLR (Single-cell Interpretation via Multi-kernel LeaRning), an open-source tool that implements a novel framework to learn a sample-to-sample similarity measure from expression data observed for heterogenous samples. SIMLR can be effectively used to perform tasks such as dimension reduction, clustering, and visualization of heterogeneous populations of samples. SIMLR was benchmarked against state-of-the-art methods for these three tasks on several public datasets, showing it to be scalable and capable of greatly improving clustering performance, as well as providing valuable insights by making the data more interpretable via better a visualization. Availability and Implementation SIMLR is available on GitHub in both R and MATLAB implementations. Furthermore, it is also available as an R package on http://bioconductor.org.
Tasks	Dimensionality Reduction
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07844v2
PDF	http://arxiv.org/pdf/1703.07844v2.pdf
PWC	https://paperswithcode.com/paper/simlr-a-tool-for-large-scale-genomic-analyses
Repo
Framework

ClustGeo: an R package for hierarchical clustering with spatial constraints


Title	ClustGeo: an R package for hierarchical clustering with spatial constraints
Authors	Marie Chavent, Vanessa Kuentz-Simonet, Amaury Labenne, Jérôme Saracco
Abstract	In this paper, we propose a Ward-like hierarchical clustering algorithm including spatial/geographical constraints. Two dissimilarity matrices $D_0$ and $D_1$ are inputted, along with a mixing parameter $\alpha \in [0,1]$. The dissimilarities can be non-Euclidean and the weights of the observations can be non-uniform. The first matrix gives the dissimilarities in the “feature space” and the second matrix gives the dissimilarities in the “constraint space”. The criterion minimized at each stage is a convex combination of the homogeneity criterion calculated with $D_0$ and the homogeneity criterion calculated with $D_1$. The idea is then to determine a value of $\alpha$ which increases the spatial contiguity without deteriorating too much the quality of the solution based on the variables of interest i.e. those of the feature space. This procedure is illustrated on a real dataset using the R package ClustGeo.
Tasks
Published	2017-07-12
URL	http://arxiv.org/abs/1707.03897v2
PDF	http://arxiv.org/pdf/1707.03897v2.pdf
PWC	https://paperswithcode.com/paper/clustgeo-an-r-package-for-hierarchical
Repo
Framework

Cultivating DNN Diversity for Large Scale Video Labelling


Title	Cultivating DNN Diversity for Large Scale Video Labelling
Authors	Mikel Bober-Irizar, Sameed Husain, Eng-Jon Ong, Miroslaw Bober
Abstract	We investigate factors controlling DNN diversity in the context of the Google Cloud and YouTube-8M Video Understanding Challenge. While it is well-known that ensemble methods improve prediction performance, and that combining accurate but diverse predictors helps, there is little knowledge on how to best promote & measure DNN diversity. We show that diversity can be cultivated by some unexpected means, such as model over-fitting or dropout variations. We also present details of our solution to the video understanding problem, which ranked #7 in the Kaggle competition (competing as the Yeti team).
Tasks	Video Understanding
Published	2017-07-13
URL	http://arxiv.org/abs/1707.04272v1
PDF	http://arxiv.org/pdf/1707.04272v1.pdf
PWC	https://paperswithcode.com/paper/cultivating-dnn-diversity-for-large-scale
Repo
Framework

Deep Learning Assisted Heuristic Tree Search for the Container Pre-marshalling Problem


Title	Deep Learning Assisted Heuristic Tree Search for the Container Pre-marshalling Problem
Authors	André Hottung, Shunji Tanaka, Kevin Tierney
Abstract	The container pre-marshalling problem (CPMP) is concerned with the re-ordering of containers in container terminals during off-peak times so that containers can be quickly retrieved when the port is busy. The problem has received significant attention in the literature and is addressed by a large number of exact and heuristic methods. Existing methods for the CPMP heavily rely on problem-specific components (e.g., proven lower bounds) that need to be developed by domain experts with knowledge of optimization techniques and a deep understanding of the problem at hand. With the goal to automate the costly and time-intensive design of heuristics for the CPMP, we propose a new method called Deep Learning Heuristic Tree Search (DLTS). It uses deep neural networks to learn solution strategies and lower bounds customized to the CPMP solely through analyzing existing (near-) optimal solutions to CPMP instances. The networks are then integrated into a tree search procedure to decide which branch to choose next and to prune the search tree. DLTS produces the highest quality heuristic solutions to the CPMP to date with gaps to optimality below 2% on real-world sized instances.
Tasks
Published	2017-09-28
URL	https://arxiv.org/abs/1709.09972v2
PDF	https://arxiv.org/pdf/1709.09972v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-assisted-heuristic-tree-search
Repo
Framework

Text Compression for Sentiment Analysis via Evolutionary Algorithms


Title	Text Compression for Sentiment Analysis via Evolutionary Algorithms
Authors	Emmanuel Dufourq, Bruce A. Bassett
Abstract	Can textual data be compressed intelligently without losing accuracy in evaluating sentiment? In this study, we propose a novel evolutionary compression algorithm, PARSEC (PARts-of-Speech for sEntiment Compression), which makes use of Parts-of-Speech tags to compress text in a way that sacrifices minimal classification accuracy when used in conjunction with sentiment analysis algorithms. An analysis of PARSEC with eight commercial and non-commercial sentiment analysis algorithms on twelve English sentiment data sets reveals that accurate compression is possible with (0%, 1.3%, 3.3%) loss in sentiment classification accuracy for (20%, 50%, 75%) data compression with PARSEC using LingPipe, the most accurate of the sentiment algorithms. Other sentiment analysis algorithms are more severely affected by compression. We conclude that significant compression of text data is possible for sentiment analysis depending on the accuracy demands of the specific application and the specific sentiment analysis algorithm used.
Tasks	Sentiment Analysis
Published	2017-09-20
URL	http://arxiv.org/abs/1709.06990v1
PDF	http://arxiv.org/pdf/1709.06990v1.pdf
PWC	https://paperswithcode.com/paper/text-compression-for-sentiment-analysis-via
Repo
Framework

Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes


Title	Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes
Authors	Hassan Abu Alhaija, Siva Karthik Mustikovela, Lars Mescheder, Andreas Geiger, Carsten Rother
Abstract	The success of deep learning in computer vision is based on availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Creating realistic 3D content is challenging on its own and requires significant human effort. In this work, we propose an alternative paradigm which combines real and synthetic data for learning semantic instance segmentation and object detection models. Exploiting the fact that not all aspects of the scene are equally important for this task, we propose to augment real-world imagery with virtual objects of the target category. Capturing real-world images at large scale is easy and cheap, and directly provides real background appearances without the need for creating complex 3D models of the environment. We present an efficient procedure to augment real images with virtual objects. This allows us to create realistic composite images which exhibit both realistic background appearance and a large number of complex object arrangements. In contrast to modeling complete 3D environments, our augmentation approach requires only a few user interactions in combination with 3D shapes of the target object. Through extensive experimentation, we conclude the right set of parameters to produce augmented data which can maximally enhance the performance of instance segmentation models. Further, we demonstrate the utility of our approach on training standard deep models for semantic instance segmentation and object detection of cars in outdoor driving scenes. We test the models trained on our augmented data on the KITTI 2015 dataset, which we have annotated with pixel-accurate ground truth, and on Cityscapes dataset. Our experiments demonstrate that models trained on augmented imagery generalize better than those trained on synthetic data or models trained on limited amount of annotated real data.
Tasks	Instance Segmentation, Object Detection, Semantic Segmentation
Published	2017-08-04
URL	http://arxiv.org/abs/1708.01566v1
PDF	http://arxiv.org/pdf/1708.01566v1.pdf
PWC	https://paperswithcode.com/paper/augmented-reality-meets-computer-vision
Repo
Framework

Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation


Title	Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
Authors	Bolin Wei, Shuai Lu, Lili Mou, Hao Zhou, Pascal Poupart, Ge Li, Zhi Jin
Abstract	This paper addresses the question: Why do neural dialog systems generate short and meaningless replies? We conjecture that, in a dialog system, an utterance may have multiple equally plausible replies, causing the deficiency of neural networks in the dialog application. We propose a systematic way to mimic the dialog scenario in a machine translation system, and manage to reproduce the phenomenon of generating short and less meaningful sentences in the translation setting, showing evidence of our conjecture.
Tasks	Machine Translation
Published	2017-12-06
URL	http://arxiv.org/abs/1712.02250v1
PDF	http://arxiv.org/pdf/1712.02250v1.pdf
PWC	https://paperswithcode.com/paper/why-do-neural-dialog-systems-generate-short
Repo
Framework

A Software-equivalent SNN Hardware using RRAM-array for Asynchronous Real-time Learning


Title	A Software-equivalent SNN Hardware using RRAM-array for Asynchronous Real-time Learning
Authors	Aditya Shukla, Vinay Kumar, Udayan Ganguly
Abstract	Spiking Neural Network (SNN) naturally inspires hardware implementation as it is based on biology. For learning, spike time dependent plasticity (STDP) may be implemented using an energy efficient waveform superposition on memristor based synapse. However, system level implementation has three challenges. First, a classic dilemma is that recognition requires current reading for short voltage$-$spikes which is disturbed by large voltage$-$waveforms that are simultaneously applied on the same memristor for real$-$time learning i.e. the simultaneous read$-$write dilemma. Second, the hardware needs to exactly replicate software implementation for easy adaptation of algorithm to hardware. Third, the devices used in hardware simulations must be realistic. In this paper, we present an approach to address the above concerns. First, the learning and recognition occurs in separate arrays simultaneously in real$-$time, asynchronously $-$ avoiding non$-$biomimetic clocking based complex signal management. Second, we show that the hardware emulates software at every stage by comparison of SPICE (circuit$-$simulator) with MATLAB (mathematical SNN algorithm implementation in software) implementations. As an example, the hardware shows 97.5 per cent accuracy in classification which is equivalent to software for a Fisher$-$Iris dataset. Third, the STDP is implemented using a model of synaptic device implemented using HfO2 memristor. We show that an increasingly realistic memristor model slightly reduces the hardware performance (85 per cent), which highlights the need to engineer RRAM characteristics specifically for SNN.
Tasks
Published	2017-04-06
URL	http://arxiv.org/abs/1704.02012v1
PDF	http://arxiv.org/pdf/1704.02012v1.pdf
PWC	https://paperswithcode.com/paper/a-software-equivalent-snn-hardware-using-rram
Repo
Framework

Structured Variational Inference for Coupled Gaussian Processes


Title	Structured Variational Inference for Coupled Gaussian Processes
Authors	Vincent Adam
Abstract	Sparse variational approximations allow for principled and scalable inference in Gaussian Process (GP) models. In settings where several GPs are part of the generative model, theses GPs are a posteriori coupled. For many applications such as regression where predictive accuracy is the quantity of interest, this coupling is not crucial. Howewer if one is interested in posterior uncertainty, it cannot be ignored. A key element of variational inference schemes is the choice of the approximate posterior parameterization. When the number of latent variables is large, mean field (MF) methods provide fast and accurate posterior means while more structured posterior lead to inference algorithm of greater computational complexity. Here, we extend previous sparse GP approximations and propose a novel parameterization of variational posteriors in the multi-GP setting allowing for fast and scalable inference capturing posterior dependencies.
Tasks	Gaussian Processes
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01131v2
PDF	http://arxiv.org/pdf/1711.01131v2.pdf
PWC	https://paperswithcode.com/paper/structured-variational-inference-for-coupled
Repo
Framework

Chord Angle Deviation using Tangent (CADT), an Efficient and Robust Contour-based Corner Detector


Title	Chord Angle Deviation using Tangent (CADT), an Efficient and Robust Contour-based Corner Detector
Authors	Mohammad Asiful Hossain, Abdul Kawsar Tushar
Abstract	Detection of corner is the most essential process in a large number of computer vision and image processing applications. We have mentioned a number of popular contour-based corner detectors in our paper. Among all these detectors chord to triangular arm angle (CTAA) has been demonstrated as the most dominant corner detector in terms of average repeatability. We introduce a new effective method to calculate the value of curvature in this paper. By demonstrating experimental results, our proposed technique outperforms CTAA and other detectors mentioned in this paper. The results exhibit that our proposed method is simple yet efficient at finding out corners more accurately and reliably.
Tasks
Published	2017-02-16
URL	http://arxiv.org/abs/1702.04843v1
PDF	http://arxiv.org/pdf/1702.04843v1.pdf
PWC	https://paperswithcode.com/paper/chord-angle-deviation-using-tangent-cadt-an
Repo
Framework

Improved Optimization of Finite Sums with Minibatch Stochastic Variance Reduced Proximal Iterations


Title	Improved Optimization of Finite Sums with Minibatch Stochastic Variance Reduced Proximal Iterations
Authors	Jialei Wang, Tong Zhang
Abstract	We present novel minibatch stochastic optimization methods for empirical risk minimization problems, the methods efficiently leverage variance reduced first-order and sub-sampled higher-order information to accelerate the convergence speed. For quadratic objectives, we prove improved iteration complexity over state-of-the-art under reasonable assumptions. We also provide empirical evidence of the advantages of our method compared to existing approaches in the literature.
Tasks	Stochastic Optimization
Published	2017-06-21
URL	http://arxiv.org/abs/1706.07001v2
PDF	http://arxiv.org/pdf/1706.07001v2.pdf
PWC	https://paperswithcode.com/paper/improved-optimization-of-finite-sums-with
Repo
Framework

Improved Coresets for Kernel Density Estimates


Title	Improved Coresets for Kernel Density Estimates
Authors	Jeff M. Phillips, Wai Ming Tai
Abstract	We study the construction of coresets for kernel density estimates. That is we show how to approximate the kernel density estimate described by a large point set with another kernel density estimate with a much smaller point set. For characteristic kernels (including Gaussian and Laplace kernels), our approximation preserves the $L_\infty$ error between kernel density estimates within error $\epsilon$, with coreset size $2/\epsilon^2$, but no other aspects of the data, including the dimension, the diameter of the point set, or the bandwidth of the kernel common to other approximations. When the dimension is unrestricted, we show this bound is tight for these kernels as well as a much broader set. This work provides a careful analysis of the iterative Frank-Wolfe algorithm adapted to this context, an algorithm called \emph{kernel herding}. This analysis unites a broad line of work that spans statistics, machine learning, and geometry. When the dimension $d$ is constant, we demonstrate much tighter bounds on the size of the coreset specifically for Gaussian kernels, showing that it is bounded by the size of the coreset for axis-aligned rectangles. Currently the best known constructive bound is $O(\frac{1}{\epsilon} \log^d \frac{1}{\epsilon})$, and non-constructively, this can be improved by $\sqrt{\log \frac{1}{\epsilon}}$. This improves the best constant dimension bounds polynomially for $d \geq 3$.
Tasks
Published	2017-10-11
URL	http://arxiv.org/abs/1710.04325v1
PDF	http://arxiv.org/pdf/1710.04325v1.pdf
PWC	https://paperswithcode.com/paper/improved-coresets-for-kernel-density
Repo
Framework

Toward Continual Learning for Conversational Agents


Title	Toward Continual Learning for Conversational Agents
Authors	Sungjin Lee
Abstract	While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the lack of modularity. Previous studies adopted a hybrid approach with knowledge-based components either to abstract out domain-specific information or to augment data to cover more diverse patterns. On the contrary, we propose to directly address the problem using recent developments in the space of continual learning for neural models. Specifically, we adopt a domain-independent neural conversational model and introduce a novel neural continual learning algorithm that allows a conversational agent to accumulate skills across different tasks in a data-efficient way. To the best of our knowledge, this is the first work that applies continual learning to conversation systems. We verified the efficacy of our method through a conversational skill transfer from either synthetic dialogs or human-human dialogs to human-computer conversations in a customer support domain.
Tasks	Continual Learning
Published	2017-12-28
URL	http://arxiv.org/abs/1712.09943v3
PDF	http://arxiv.org/pdf/1712.09943v3.pdf
PWC	https://paperswithcode.com/paper/toward-continual-learning-for-conversational
Repo
Framework