October 20, 2019

2717 words 13 mins read

Paper Group ANR 59

Deep learning: Extrapolation tool for ab initio nuclear theory. Learning Traffic Flow Dynamics using Random Fields. A Machine Learning-based Recommendation System for Swaptions Strategies. Learning a Local Feature Descriptor for 3D LiDAR Scans. Position Estimation of Camera Based on Unsupervised Learning. Learning to Repair Software Vulnerabilities …

Deep learning: Extrapolation tool for ab initio nuclear theory


Title	Deep learning: Extrapolation tool for ab initio nuclear theory
Authors	Gianina Alina Negoita, James P. Vary, Glenn R. Luecke, Pieter Maris, Andrey M. Shirokov, Ik Jae Shin, Youngman Kim, Esmond G. Ng, Chao Yang, Matthew Lockner, Gurpur M. Prabhu
Abstract	Ab initio approaches in nuclear theory, such as the no-core shell model (NCSM), have been developed for approximately solving finite nuclei with realistic strong interactions. The NCSM and other approaches require an extrapolation of the results obtained in a finite basis space to the infinite basis space limit and assessment of the uncertainty of those extrapolations. Each observable requires a separate extrapolation and most observables have no proven extrapolation method. We propose a feed-forward artificial neural network (ANN) method as an extrapolation tool to obtain the ground state energy and the ground state point-proton root-mean-square (rms) radius along with their extrapolation uncertainties. The designed ANNs are sufficient to produce results for these two very different observables in $^6$Li from the ab initio NCSM results in small basis spaces that satisfy the following theoretical physics condition: independence of basis space parameters in the limit of extremely large matrices. Comparisons of the ANN results with other extrapolation methods are also provided.
Tasks
Published	2018-10-06
URL	https://arxiv.org/abs/1810.04009v4
PDF	https://arxiv.org/pdf/1810.04009v4.pdf
PWC	https://paperswithcode.com/paper/deep-learning-extrapolation-tool-for-ab
Repo
Framework

Learning Traffic Flow Dynamics using Random Fields


Title	Learning Traffic Flow Dynamics using Random Fields
Authors	Saif Eddin Jabari, Deepthi Mary Dilip, DianChao Lin, Bilal Thonnam Thodi
Abstract	This paper presents a mesoscopic traffic flow model that explicitly describes the spatio-temporal evolution of the probability distributions of vehicle trajectories. The dynamics are represented by a sequence of factor graphs, which enable learning of traffic dynamics from limited Lagrangian measurements using an efficient message passing technique. The approach ensures that estimated speeds and traffic densities are non-negative with probability one. The estimation technique is tested using vehicle trajectory datasets generated using an independent microscopic traffic simulator and is shown to efficiently reproduce traffic conditions with probe vehicle penetration levels as little as 10%. The proposed algorithm is also compared with state-of-the-art traffic state estimation techniques developed for the same purpose and it is shown that the proposed approach can outperform the state-of-the-art techniques in terms reconstruction accuracy.
Tasks	Autonomous Vehicles
Published	2018-06-22
URL	https://arxiv.org/abs/1806.08764v2
PDF	https://arxiv.org/pdf/1806.08764v2.pdf
PWC	https://paperswithcode.com/paper/learning-traffic-flow-dynamics-using-random
Repo
Framework

A Machine Learning-based Recommendation System for Swaptions Strategies


Title	A Machine Learning-based Recommendation System for Swaptions Strategies
Authors	Adriano Soares Koshiyama, Nick Firoozye, Philip Treleaven
Abstract	Derivative traders are usually required to scan through hundreds, even thousands of possible trades on a daily basis. Up to now, not a single solution is available to aid in their job. Hence, this work aims to develop a trading recommendation system, and apply this system to the so-called Mid-Curve Calendar Spread (MCCS), an exotic swaption-based derivatives package. In summary, our trading recommendation system follows this pipeline: (i) on a certain trade date, we compute metrics and sensitivities related to an MCCS; (ii) these metrics are feed in a model that can predict its expected return for a given holding period; and after repeating (i) and (ii) for all trades we (iii) rank the trades using some dominance criteria. To suggest that such approach is feasible, we used a list of 35 different types of MCCS; a total of 11 predictive models; and 4 benchmark models. Our results suggest that in general linear regression with lasso regularisation compared favourably to other approaches from a predictive and interpretability perspective.
Tasks
Published	2018-10-04
URL	http://arxiv.org/abs/1810.02125v1
PDF	http://arxiv.org/pdf/1810.02125v1.pdf
PWC	https://paperswithcode.com/paper/a-machine-learning-based-recommendation
Repo
Framework

Learning a Local Feature Descriptor for 3D LiDAR Scans


Title	Learning a Local Feature Descriptor for 3D LiDAR Scans
Authors	Ayush Dewan, Tim Caselitz, Wolfram Burgard
Abstract	Robust data association is necessary for virtually every SLAM system and finding corresponding points is typically a preprocessing step for scan alignment algorithms. Traditionally, handcrafted feature descriptors were used for these problems but recently learned descriptors have been shown to perform more robustly. In this work, we propose a local feature descriptor for 3D LiDAR scans. The descriptor is learned using a Convolutional Neural Network (CNN). Our proposed architecture consists of a Siamese network for learning a feature descriptor and a metric learning network for matching the descriptors. We also present a method for estimating local surface patches and obtaining ground-truth correspondences. In extensive experiments, we compare our learned feature descriptor with existing 3D local descriptors and report highly competitive results for multiple experiments in terms of matching accuracy and computation time. \end{abstract}
Tasks	Metric Learning
Published	2018-09-20
URL	http://arxiv.org/abs/1809.07494v1
PDF	http://arxiv.org/pdf/1809.07494v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-local-feature-descriptor-for-3d
Repo
Framework

Position Estimation of Camera Based on Unsupervised Learning


Title	Position Estimation of Camera Based on Unsupervised Learning
Authors	YanTong Wu, Yang Liu
Abstract	It is an exciting task to recover the scene’s 3d-structure and camera pose from the video sequence. Most of the current solutions divide it into two parts, monocular depth recovery and camera pose estimation. The monocular depth recovery is often studied as an independent part, and a better depth estimation is used to solve the pose. While camera pose is still estimated by traditional SLAM (Simultaneous Localization And Mapping) methods in most cases. The use of unsupervised method for monocular depth recovery and pose estimation has benefited from the study of [1] and achieved good results. In this paper, we improve the method of [1]. Our emphasis is laid on the improvement of the idea and related theory, introducing a more reasonable inter frame constraints and finally synthesize the camera trajectory with inter frame pose estimation in the unified world coordinate system. And our results get better performance.
Tasks	Depth Estimation, Pose Estimation, Simultaneous Localization and Mapping
Published	2018-05-05
URL	http://arxiv.org/abs/1805.02020v1
PDF	http://arxiv.org/pdf/1805.02020v1.pdf
PWC	https://paperswithcode.com/paper/position-estimation-of-camera-based-on
Repo
Framework

Learning to Repair Software Vulnerabilities with Generative Adversarial Networks


Title	Learning to Repair Software Vulnerabilities with Generative Adversarial Networks
Authors	Jacob Harer, Onur Ozdemir, Tomo Lazovich, Christopher P. Reale, Rebecca L. Russell, Louis Y. Kim, Peter Chin
Abstract	Motivated by the problem of automated repair of software vulnerabilities, we propose an adversarial learning approach that maps from one discrete source domain to another target domain without requiring paired labeled examples or source and target domains to be bijections. We demonstrate that the proposed adversarial learning approach is an effective technique for repairing software vulnerabilities, performing close to seq2seq approaches that require labeled pairs. The proposed Generative Adversarial Network approach is application-agnostic in that it can be applied to other problems similar to code repair, such as grammar correction or sentiment translation.
Tasks
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07475v3
PDF	http://arxiv.org/pdf/1805.07475v3.pdf
PWC	https://paperswithcode.com/paper/learning-to-repair-software-vulnerabilities
Repo
Framework

Overlapping Clustering Models, and One (class) SVM to Bind Them All


Title	Overlapping Clustering Models, and One (class) SVM to Bind Them All
Authors	Xueyu Mao, Purnamrita Sarkar, Deepayan Chakrabarti
Abstract	People belong to multiple communities, words belong to multiple topics, and books cover multiple genres; overlapping clusters are commonplace. Many existing overlapping clustering methods model each person (or word, or book) as a non-negative weighted combination of “exemplars” who belong solely to one community, with some small noise. Geometrically, each person is a point on a cone whose corners are these exemplars. This basic form encompasses the widely used Mixed Membership Stochastic Blockmodel of networks (Airoldi et al., 2008) and its degree-corrected variants (Jin et al., 2017), as well as topic models such as LDA (Blei et al., 2003). We show that a simple one-class SVM yields provably consistent parameter inference for all such models, and scales to large datasets. Experimental results on several simulated and real datasets show our algorithm (called SVM-cone) is both accurate and scalable.
Tasks	Topic Models
Published	2018-06-18
URL	http://arxiv.org/abs/1806.06945v2
PDF	http://arxiv.org/pdf/1806.06945v2.pdf
PWC	https://paperswithcode.com/paper/overlapping-clustering-models-and-one-class
Repo
Framework

Automatic Stance Detection Using End-to-End Memory Networks


Title	Automatic Stance Detection Using End-to-End Memory Networks
Authors	Mitra Mohtarami, Ramy Baly, James Glass, Preslav Nakov, Lluis Marquez, Alessandro Moschitti
Abstract	We present a novel end-to-end memory network for stance detection, which jointly (i) predicts whether a document agrees, disagrees, discusses or is unrelated with respect to a given target claim, and also (ii) extracts snippets of evidence for that prediction. The network operates at the paragraph level and integrates convolutional and recurrent neural networks, as well as a similarity matrix as part of the overall architecture. The experimental evaluation on the Fake News Challenge dataset shows state-of-the-art performance.
Tasks	Stance Detection
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07581v1
PDF	http://arxiv.org/pdf/1804.07581v1.pdf
PWC	https://paperswithcode.com/paper/automatic-stance-detection-using-end-to-end
Repo
Framework

Nonparametric Bayesian Lomax delegate racing for survival analysis with competing risks


Title	Nonparametric Bayesian Lomax delegate racing for survival analysis with competing risks
Authors	Quan Zhang, Mingyuan Zhou
Abstract	We propose Lomax delegate racing (LDR) to explicitly model the mechanism of survival under competing risks and to interpret how the covariates accelerate or decelerate the time to event. LDR explains non-monotonic covariate effects by racing a potentially infinite number of sub-risks, and consequently relaxes the ubiquitous proportional-hazards assumption which may be too restrictive. Moreover, LDR is naturally able to model not only censoring, but also missing event times or event types. For inference, we develop a Gibbs sampler under data augmentation for moderately sized data, along with a stochastic gradient descent maximum a posteriori inference algorithm for big data applications. Illustrative experiments are provided on both synthetic and real datasets, and comparison with various benchmark algorithms for survival analysis with competing risks demonstrates distinguished performance of LDR.
Tasks	Data Augmentation, Survival Analysis
Published	2018-10-19
URL	http://arxiv.org/abs/1810.08564v2
PDF	http://arxiv.org/pdf/1810.08564v2.pdf
PWC	https://paperswithcode.com/paper/nonparametric-bayesian-lomax-delegate-racing
Repo
Framework

Scene Coordinate and Correspondence Learning for Image-Based Localization


Title	Scene Coordinate and Correspondence Learning for Image-Based Localization
Authors	Mai Bui, Shadi Albarqouni, Slobodan Ilic, Nassir Navab
Abstract	Scene coordinate regression has become an essential part of current camera re-localization methods. Different versions, such as regression forests and deep learning methods, have been successfully applied to estimate the corresponding camera pose given a single input image. In this work, we propose to regress the scene coordinates pixel-wise for a given RGB image by using deep learning. Compared to the recent methods, which usually employ RANSAC to obtain a robust pose estimate from the established point correspondences, we propose to regress confidences of these correspondences, which allows us to immediately discard erroneous predictions and improve the initial pose estimates. Finally, the resulting confidences can be used to score initial pose hypothesis and aid in pose refinement, offering a generalized solution to solve this task.
Tasks	Image-Based Localization
Published	2018-05-22
URL	http://arxiv.org/abs/1805.08443v4
PDF	http://arxiv.org/pdf/1805.08443v4.pdf
PWC	https://paperswithcode.com/paper/scene-coordinate-and-correspondence-learning
Repo
Framework

Exploring $k$ out of Top $ρ$ Fraction of Arms in Stochastic Bandits


Title	Exploring $k$ out of Top $ρ$ Fraction of Arms in Stochastic Bandits
Authors	Wenbo Ren, Jia Liu, Ness Shroff
Abstract	This paper studies the problem of identifying any $k$ distinct arms among the top $\rho$ fraction (e.g., top 5%) of arms from a finite or infinite set with a probably approximately correct (PAC) tolerance $\epsilon$. We consider two cases: (i) when the threshold of the top arms’ expected rewards is known and (ii) when it is unknown. We prove lower bounds for the four variants (finite or infinite, and threshold known or unknown), and propose algorithms for each. Two of these algorithms are shown to be sample complexity optimal (up to constant factors) and the other two are optimal up to a log factor. Results in this paper provide up to $\rho n/k$ reductions compared with the “$k$-exploration” algorithms that focus on finding the (PAC) best $k$ arms out of $n$ arms. We also numerically show improvements over the state-of-the-art.
Tasks
Published	2018-10-28
URL	http://arxiv.org/abs/1810.11857v1
PDF	http://arxiv.org/pdf/1810.11857v1.pdf
PWC	https://paperswithcode.com/paper/exploring-k-out-of-top-fraction-of-arms-in
Repo
Framework

Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning


Title	Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning
Authors	Wanjia Liu, Huaijin Chen, Rishab Goel, Yuzhong Huang, Ashok Veeraraghavan, Ankit Patel
Abstract	Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks. In such framework, besides the regular ConvNets responsible for RGB frame inputs, a second network is introduced to handle the temporal representation, usually the optical flow (OF). However, OF or other task-oriented flow is computationally costly, and is thus typically pre-computed. Critically, this prevents the two-stream approach from being applied to reinforcement learning (RL) applications such as video game playing, where the next state depends on current state and action choices. Inspired by the early vision systems of mammals and insects, we propose a fast event-driven representation (EDR) that models several major properties of early retinal circuits: (1) logarithmic input response, (2) multi-timescale temporal smoothing to filter noise, and (3) bipolar (ON/OFF) pathways for primitive event detection[12]. Trading off the directional information for fast speed (> 9000 fps), EDR en-ables fast real-time inference/learning in video applications that require interaction between an agent and the world such as game-playing, virtual robotics, and domain adaptation. In this vein, we use EDR to demonstrate performance improvements over state-of-the-art reinforcement learning algorithms for Atari games, something that has not been possible with pre-computed OF. Moreover, with UCF-101 video action recognition experiments, we show that EDR performs near state-of-the-art in accuracy while achieving a 1,500x speedup in input representation processing, as compared to optical flow.
Tasks	Atari Games, Domain Adaptation, Optical Flow Estimation, Temporal Action Localization, Video Recognition, Video Understanding
Published	2018-05-16
URL	http://arxiv.org/abs/1805.06374v2
PDF	http://arxiv.org/pdf/1805.06374v2.pdf
PWC	https://paperswithcode.com/paper/fast-retinomorphic-event-stream-for-video
Repo
Framework


Title	Double Refinement Network for Efficient Indoor Monocular Depth Estimation
Authors	Nikita Durasov, Mikhail Romanov, Valeriya Bubnova, Pavel Bogomolov, Anton Konushin
Abstract	Monocular depth estimation is the task of obtaining a measure of distance for each pixel using a single image. It is an important problem in computer vision and is usually solved using neural networks. Though recent works in this area have shown significant improvement in accuracy, the state-of-the-art methods tend to require massive amounts of memory and time to process an image. The main purpose of this work is to improve the performance of the latest solutions with no decrease in accuracy. To this end, we introduce the Double Refinement Network architecture. The proposed method achieves state-of-the-art results on the standard benchmark RGB-D dataset NYU Depth v2, while its frames per second rate is significantly higher (up to 18 times speedup per image at batch size 1) and the RAM usage per image is lower.
Tasks	Depth Estimation, Indoor Monocular Depth Estimation, Monocular Depth Estimation
Published	2018-11-20
URL	http://arxiv.org/abs/1811.08466v2
PDF	http://arxiv.org/pdf/1811.08466v2.pdf
PWC	https://paperswithcode.com/paper/double-refinement-network-for-efficient
Repo
Framework

LSTMs with Attention for Aggression Detection


Title	LSTMs with Attention for Aggression Detection
Authors	Nishant Nikhil, Ramit Pahwa, Mehul Kumar Nirala, Rohan Khilnani
Abstract	In this paper, we describe the system submitted for the shared task on Aggression Identification in Facebook posts and comments by the team Nishnik. Previous works demonstrate that LSTMs have achieved remarkable performance in natural language processing tasks. We deploy an LSTM model with an attention unit over it. Our system ranks 6th and 4th in the Hindi subtask for Facebook comments and subtask for generalized social media data respectively. And it ranks 17th and 10th in the corresponding English subtasks.
Tasks
Published	2018-07-16
URL	http://arxiv.org/abs/1807.06151v1
PDF	http://arxiv.org/pdf/1807.06151v1.pdf
PWC	https://paperswithcode.com/paper/lstms-with-attention-for-aggression-detection
Repo
Framework

A brief introduction to the Grey Machine Learning


Title	A brief introduction to the Grey Machine Learning
Authors	Xin Ma
Abstract	This paper presents a brief introduction to the key points of the Grey Machine Learning (GML) based on the kernels. The general formulation of the grey system models have been firstly summarized, and then the nonlinear extension of the grey models have been developed also with general formulations. The kernel implicit mapping is used to estimate the nonlinear function of the GML model, by extending the nonparametric formulation of the LSSVM, the estimation of the nonlinear function of the GML model can also be expressed by the kernels. A short discussion on the priority of this new framework to the existing grey models and LSSVM have also been discussed in this paper. And the perspectives and future orientations of this framework have also been presented.
Tasks
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01745v2
PDF	http://arxiv.org/pdf/1805.01745v2.pdf
PWC	https://paperswithcode.com/paper/a-brief-introduction-to-the-grey-machine
Repo
Framework