July 28, 2019

3081 words 15 mins read

Paper Group ANR 439

Automating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing. How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility. Probabilistic Program Abstractions. A deep level set method for image segmentation. Basic Thresholding Classification. Size Matters: Cardinality-Constrained C …

Automating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing


Title	Automating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing
Authors	Mogens Graf Plessen
Abstract	Within the context of autonomous driving a model-based reinforcement learning algorithm is proposed for the design of neural network-parameterized controllers. Classical model-based control methods, which include sampling- and lattice-based algorithms and model predictive control, suffer from the trade-off between model complexity and computational burden required for the online solution of expensive optimization or search problems at every short sampling time. To circumvent this trade-off, a 2-step procedure is motivated: first learning of a controller during offline training based on an arbitrarily complicated mathematical system model, before online fast feedforward evaluation of the trained controller. The contribution of this paper is the proposition of a simple gradient-free and model-based algorithm for deep reinforcement learning using task separation with hill climbing (TSHC). In particular, (i) simultaneous training on separate deterministic tasks with the purpose of encoding many motion primitives in a neural network, and (ii) the employment of maximally sparse rewards in combination with virtual velocity constraints (VVCs) in setpoint proximity are advocated.
Tasks	Autonomous Driving
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10785v2
PDF	http://arxiv.org/pdf/1711.10785v2.pdf
PWC	https://paperswithcode.com/paper/automating-vehicles-by-deep-reinforcement
Repo
Framework

How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility


Title	How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility
Authors	Allison J. B. Chaney, Brandon M. Stewart, Barbara E. Engelhardt
Abstract	Recommendation systems are ubiquitous and impact many domains; they have the potential to influence product consumption, individuals’ perceptions of the world, and life-altering decisions. These systems are often evaluated or trained with data from users already exposed to algorithmic recommendations; this creates a pernicious feedback loop. Using simulations, we demonstrate how using data confounded in this way homogenizes user behavior without increasing utility.
Tasks	Recommendation Systems
Published	2017-10-30
URL	http://arxiv.org/abs/1710.11214v2
PDF	http://arxiv.org/pdf/1710.11214v2.pdf
PWC	https://paperswithcode.com/paper/how-algorithmic-confounding-in-recommendation
Repo
Framework

Probabilistic Program Abstractions


Title	Probabilistic Program Abstractions
Authors	Steven Holtzen, Todd Millstein, Guy Van den Broeck
Abstract	Abstraction is a fundamental tool for reasoning about complex systems. Program abstraction has been utilized to great effect for analyzing deterministic programs. At the heart of program abstraction is the relationship between a concrete program, which is difficult to analyze, and an abstract program, which is more tractable. Program abstractions, however, are typically not probabilistic. We generalize non-deterministic program abstractions to probabilistic program abstractions by explicitly quantifying the non-deterministic choices. Our framework upgrades key definitions and properties of abstractions to the probabilistic context. We also discuss preliminary ideas for performing inference on probabilistic abstractions and general probabilistic programs.
Tasks
Published	2017-05-28
URL	http://arxiv.org/abs/1705.09970v2
PDF	http://arxiv.org/pdf/1705.09970v2.pdf
PWC	https://paperswithcode.com/paper/probabilistic-program-abstractions
Repo
Framework

A deep level set method for image segmentation


Title	A deep level set method for image segmentation
Authors	Min Tang, Sepehr Valipour, Zichen Vincent Zhang, Dana Cobzas, MartinJagersand
Abstract	This paper proposes a novel image segmentation approachthat integrates fully convolutional networks (FCNs) with a level setmodel. Compared with a FCN, the integrated method can incorporatesmoothing and prior information to achieve an accurate segmentation.Furthermore, different than using the level set model as a post-processingtool, we integrate it into the training phase to fine-tune the FCN. Thisallows the use of unlabeled data during training in a semi-supervisedsetting. Using two types of medical imaging data (liver CT and left ven-tricle MRI data), we show that the integrated method achieves goodperformance even when little training data is available, outperformingthe FCN or the level set model alone.
Tasks	Semantic Segmentation
Published	2017-05-17
URL	http://arxiv.org/abs/1705.06260v2
PDF	http://arxiv.org/pdf/1705.06260v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-level-set-method-for-image
Repo
Framework

Basic Thresholding Classification


Title	Basic Thresholding Classification
Authors	Mehmet Altan Toksöz
Abstract	In this thesis, we propose a light-weight sparsity-based algorithm, basic thresholding classifier (BTC), for classification applications (such as face identification, hyper-spectral image classification, etc.) which is capable of identifying test samples extremely rapidly and performing high classification accuracy. Originally BTC is a linear classifier which works based on the assumption that the samples of the classes of a given dataset are linearly separable. However, in practice those samples may not be linearly separable. In this context, we also propose another algorithm namely kernel basic thresholding classifier (KBTC) which is a non-linear kernel version of the BTC algorithm. KBTC can achieve promising results especially when the given samples are linearly non-separable. For both proposals, we introduce sufficient identification conditions (SICs) under which BTC and KBTC can identify any test sample in the range space of a given dictionary. By using SICs, we develop parameter estimation procedures which do not require any cross validation. Both BTC and KBTC algorithms provide efficient classifier fusion schemes in which individual classifier outputs are combined to produce better classification results. For instance, for the application of face identification, this is done by combining the residuals having different random projectors. For spatial applications such as hyper-spectral image classification, the fusion is carried out by incorporating the spatial information, in which the output residual maps are filtered using a smoothing filter. Numerical results on publicly available face and hyper-spectral datasets show that our proposal outperforms well-known support vector machines (SVM)-based techniques, multinomial logistic regression (MLR)-based methods, and sparsity-based approaches like $l_1$-minimization and simultaneous orthogonal matching pursuit (SOMP).
Tasks	Face Identification, Image Classification
Published	2017-12-08
URL	http://arxiv.org/abs/1712.03217v1
PDF	http://arxiv.org/pdf/1712.03217v1.pdf
PWC	https://paperswithcode.com/paper/basic-thresholding-classification
Repo
Framework

Size Matters: Cardinality-Constrained Clustering and Outlier Detection via Conic Optimization


Title	Size Matters: Cardinality-Constrained Clustering and Outlier Detection via Conic Optimization
Authors	Napat Rujeerapaiboon, Kilian Schindler, Daniel Kuhn, Wolfram Wiesemann
Abstract	Plain vanilla K-means clustering has proven to be successful in practice, yet it suffers from outlier sensitivity and may produce highly unbalanced clusters. To mitigate both shortcomings, we formulate a joint outlier detection and clustering problem, which assigns a prescribed number of datapoints to an auxiliary outlier cluster and performs cardinality-constrained K-means clustering on the residual dataset, treating the cluster cardinalities as a given input. We cast this problem as a mixed-integer linear program (MILP) that admits tractable semidefinite and linear programming relaxations. We propose deterministic rounding schemes that transform the relaxed solutions to feasible solutions for the MILP. We also prove that these solutions are optimal in the MILP if a cluster separation condition holds.
Tasks	Outlier Detection
Published	2017-05-22
URL	http://arxiv.org/abs/1705.07837v3
PDF	http://arxiv.org/pdf/1705.07837v3.pdf
PWC	https://paperswithcode.com/paper/size-matters-cardinality-constrained
Repo
Framework

Fairness Testing: Testing Software for Discrimination


Title	Fairness Testing: Testing Software for Discrimination
Authors	Sainyam Galhotra, Yuriy Brun, Alexandra Meliou
Abstract	This paper defines software fairness and discrimination and develops a testing-based method for measuring if and how much software discriminates, focusing on causality in discriminatory behavior. Evidence of software discrimination has been found in modern software systems that recommend criminal sentences, grant access to financial products, and determine who is allowed to participate in promotions. Our approach, Themis, generates efficient test suites to measure discrimination. Given a schema describing valid system inputs, Themis generates discrimination tests automatically and does not require an oracle. We evaluate Themis on 20 software systems, 12 of which come from prior work with explicit focus on avoiding discrimination. We find that (1) Themis is effective at discovering software discrimination, (2) state-of-the-art techniques for removing discrimination from algorithms fail in many situations, at times discriminating against as much as 98% of an input subdomain, (3) Themis optimizations are effective at producing efficient test suites for measuring discrimination, and (4) Themis is more efficient on systems that exhibit more discrimination. We thus demonstrate that fairness testing is a critical aspect of the software development cycle in domains with possible discrimination and provide initial tools for measuring software discrimination.
Tasks
Published	2017-09-11
URL	http://arxiv.org/abs/1709.03221v1
PDF	http://arxiv.org/pdf/1709.03221v1.pdf
PWC	https://paperswithcode.com/paper/fairness-testing-testing-software-for
Repo
Framework

Predicting shim gaps in aircraft assembly with machine learning and sparse sensing


Title	Predicting shim gaps in aircraft assembly with machine learning and sparse sensing
Authors	Krithika Manohar, Thomas Hogan, Jim Buttrick, Ashis G. Banerjee, J. Nathan Kutz, Steven L. Brunton
Abstract	A modern aircraft may require on the order of thousands of custom shims to fill gaps between structural components in the airframe that arise due to manufacturing tolerances adding up across large structures. These shims are necessary to eliminate gaps, maintain structural performance, and minimize pull-down forces required to bring the aircraft into engineering nominal configuration for peak aerodynamic efficiency. Gap filling is a time-consuming process, involving either expensive by-hand inspection or computations on vast quantities of measurement data from increasingly sophisticated metrology equipment. Either case amounts to significant delays in production, with much of the time spent in the critical path of aircraft assembly. This work presents an alternative strategy for predictive shimming, based on machine learning and sparse sensing to first learn gap distributions from historical data, and then design optimized sparse sensing strategies to streamline data collection and processing. This new approach is based on the assumption that patterns exist in shim distributions across aircraft, which may be mined and used to reduce the burden of data collection and processing in future aircraft. Specifically, robust principal component analysis is used to extract low-dimensional patterns in the gap measurements while rejecting outliers. Next, optimized sparse sensors are obtained that are most informative about the dimensions of a new aircraft in these low-dimensional principal components. We demonstrate the success of the proposed approach, called PIXel Identification Despite Uncertainty in Sensor Technology (PIXI-DUST), on historical production data from 54 representative Boeing commercial aircraft. Our algorithm successfully predicts $99%$ of shim gaps within the desired measurement tolerance using $3%$ of the laser scan points typically required; all results are cross-validated.
Tasks
Published	2017-11-24
URL	http://arxiv.org/abs/1711.08861v1
PDF	http://arxiv.org/pdf/1711.08861v1.pdf
PWC	https://paperswithcode.com/paper/predicting-shim-gaps-in-aircraft-assembly
Repo
Framework

A case study of Empirical Bayes in User-Movie Recommendation system


Title	A case study of Empirical Bayes in User-Movie Recommendation system
Authors	Arabin Kumar Dey, Raghav Somani, Sreangsu Acharyya
Abstract	In this article we provide a formulation of empirical bayes described by Atchade (2011) to tune the hyperparameters of priors used in bayesian set up of collaborative filter. We implement the same in MovieLens small dataset. We see that it can be used to get a good initial choice for the parameters. It can also be used to guess an initial choice for hyper-parameters in grid search procedure even for the datasets where MCMC oscillates around the true value or takes long time to converge.
Tasks
Published	2017-07-07
URL	http://arxiv.org/abs/1707.02294v1
PDF	http://arxiv.org/pdf/1707.02294v1.pdf
PWC	https://paperswithcode.com/paper/a-case-study-of-empirical-bayes-in-user-movie
Repo
Framework

Online Learning of Power Transmission Dynamics


Title	Online Learning of Power Transmission Dynamics
Authors	Andrey Y. Lokhov, Marc Vuffray, Dmitry Shemetov, Deepjyoti Deka, Michael Chertkov
Abstract	We consider the problem of reconstructing the dynamic state matrix of transmission power grids from time-stamped PMU measurements in the regime of ambient fluctuations. Using a maximum likelihood based approach, we construct a family of convex estimators that adapt to the structure of the problem depending on the available prior information. The proposed method is fully data-driven and does not assume any knowledge of system parameters. It can be implemented in near real-time and requires a small amount of data. Our learning algorithms can be used for model validation and calibration, and can also be applied to related problems of system stability, detection of forced oscillations, generation re-dispatch, as well as to the estimation of the system state.
Tasks	Calibration
Published	2017-10-27
URL	http://arxiv.org/abs/1710.10021v1
PDF	http://arxiv.org/pdf/1710.10021v1.pdf
PWC	https://paperswithcode.com/paper/online-learning-of-power-transmission
Repo
Framework

Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization


Title	Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization
Authors	Kamran Ghasedi Dizaji, Amirhossein Herandi, Cheng Deng, Weidong Cai, Heng Huang
Abstract	Image clustering is one of the most important computer vision applications, which has been extensively studied in literature. However, current clustering methods mostly suffer from lack of efficiency and scalability when dealing with large-scale and high-dimensional data. In this paper, we propose a new clustering model, called DEeP Embedded RegularIzed ClusTering (DEPICT), which efficiently maps data into a discriminative embedding subspace and precisely predicts cluster assignments. DEPICT generally consists of a multinomial logistic regression function stacked on top of a multi-layer convolutional autoencoder. We define a clustering objective function using relative entropy (KL divergence) minimization, regularized by a prior for the frequency of cluster assignments. An alternating strategy is then derived to optimize the objective by updating parameters and estimating cluster assignments. Furthermore, we employ the reconstruction loss functions in our autoencoder, as a data-dependent regularization term, to prevent the deep embedding function from overfitting. In order to benefit from end-to-end optimization and eliminate the necessity for layer-wise pretraining, we introduce a joint learning framework to minimize the unified clustering and reconstruction loss functions together and train all network layers simultaneously. Experimental results indicate the superiority and faster running time of DEPICT in real-world clustering tasks, where no labeled data is available for hyper-parameter tuning.
Tasks	Image Clustering
Published	2017-04-20
URL	http://arxiv.org/abs/1704.06327v3
PDF	http://arxiv.org/pdf/1704.06327v3.pdf
PWC	https://paperswithcode.com/paper/deep-clustering-via-joint-convolutional
Repo
Framework

Driving Behavior Analysis through CAN Bus Data in an Uncontrolled Environment


Title	Driving Behavior Analysis through CAN Bus Data in an Uncontrolled Environment
Authors	Umberto Fugiglando, Emanuele Massaro, Paolo Santi, Sebastiano Milardo, Kacem Abida, Rainer Stahlmann, Florian Netter, Carlo Ratti
Abstract	Cars can nowadays record several thousands of signals through the CAN bus technology and potentially provide real-time information on the car, the driver and the surrounding environment. This paper proposes a new method for the analysis and classification of driver behavior using a selected subset of CAN bus signals, specifically gas pedal position, brake pedal pressure, steering wheel angle, steering wheel momentum, velocity, RPM, frontal and lateral acceleration. Data has been collected in a completely uncontrolled experiment, where 64 people drove 10 cars for or a total of over 2000 driving trips without any type of pre-determined driving instruction on a wide variety of road scenarios. We propose an unsupervised learning technique that clusters drivers in different groups, and offers a validation method to test the robustness of clustering in a wide range of experimental settings. The minimal amount of data needed to preserve robust driver clustering is also computed. The presented study provides a new methodology for near-real-time classification of driver behavior in uncontrolled environments.
Tasks
Published	2017-10-09
URL	http://arxiv.org/abs/1710.04133v1
PDF	http://arxiv.org/pdf/1710.04133v1.pdf
PWC	https://paperswithcode.com/paper/driving-behavior-analysis-through-can-bus
Repo
Framework

Community Aware Random Walk for Network Embedding


Title	Community Aware Random Walk for Network Embedding
Authors	Mohammad Mehdi Keikha, Maseud Rahgozar, Masoud Asadpour
Abstract	Social network analysis provides meaningful information about behavior of network members that can be used for diverse applications such as classification, link prediction. However, network analysis is computationally expensive because of feature learning for different applications. In recent years, many researches have focused on feature learning methods in social networks. Network embedding represents the network in a lower dimensional representation space with the same properties which presents a compressed representation of the network. In this paper, we introduce a novel algorithm named “CARE” for network embedding that can be used for different types of networks including weighted, directed and complex. Current methods try to preserve local neighborhood information of nodes, whereas the proposed method utilizes local neighborhood and community information of network nodes to cover both local and global structure of social networks. CARE builds customized paths, which are consisted of local and global structure of network nodes, as a basis for network embedding and uses the Skip-gram model to learn representation vector of nodes. Subsequently, stochastic gradient descent is applied to optimize our objective function and learn the final representation of nodes. Our method can be scalable when new nodes are appended to network without information loss. Parallelize generation of customized random walks is also used for speeding up CARE. We evaluate the performance of CARE on multi label classification and link prediction tasks. Experimental results on various networks indicate that the proposed method outperforms others in both Micro and Macro-f1 measures for different size of training data.
Tasks	Link Prediction, Multi-Label Classification, Network Embedding
Published	2017-10-14
URL	http://arxiv.org/abs/1710.05199v2
PDF	http://arxiv.org/pdf/1710.05199v2.pdf
PWC	https://paperswithcode.com/paper/community-aware-random-walk-for-network
Repo
Framework

Concept Formation and Dynamics of Repeated Inference in Deep Generative Models


Title	Concept Formation and Dynamics of Repeated Inference in Deep Generative Models
Authors	Yoshihiro Nagano, Ryo Karakida, Masato Okada
Abstract	Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denoise cluttered images and improve the quality of inferred results. However, previous studies only qualitatively evaluated image outputs in data space, and the mechanism behind the inference has not been investigated. The purpose of the current study is to numerically analyze changes in activity patterns of neurons in the latent space of a deep generative model called a “variational auto-encoder” (VAE). What kinds of inference dynamics the VAE demonstrates when noise is added to the input data are identified. The VAE embeds a dataset with clear cluster structures in the latent space and the center of each cluster of multiple correlated data points (memories) is referred as the concept. Our study demonstrated that transient dynamics of inference first approaches a concept, and then moves close to a memory. Moreover, the VAE revealed that the inference dynamics approaches a more abstract concept to the extent that the uncertainty of input data increases due to noise. It was demonstrated that by increasing the number of the latent variables, the trend of the inference dynamics to approach a concept can be enhanced, and the generalization ability of the VAE can be improved.
Tasks	Image Generation
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04195v1
PDF	http://arxiv.org/pdf/1712.04195v1.pdf
PWC	https://paperswithcode.com/paper/concept-formation-and-dynamics-of-repeated
Repo
Framework

Skeleton-aided Articulated Motion Generation


Title	Skeleton-aided Articulated Motion Generation
Authors	Yichao Yan, Jingwei Xu, Bingbing Ni, Xiaokang Yang
Abstract	This work make the first attempt to generate articulated human motion sequence from a single image. On the one hand, we utilize paired inputs including human skeleton information as motion embedding and a single human image as appearance reference, to generate novel motion frames, based on the conditional GAN infrastructure. On the other hand, a triplet loss is employed to pursue appearance-smoothness between consecutive frames. As the proposed framework is capable of jointly exploiting the image appearance space and articulated/kinematic motion space, it generates realistic articulated motion sequence, in contrast to most previous video generation methods which yield blurred motion effects. We test our model on two human action datasets including KTH and Human3.6M, and the proposed framework generates very promising results on both datasets.
Tasks	Gesture-to-Gesture Translation, Video Generation
Published	2017-07-04
URL	http://arxiv.org/abs/1707.01058v2
PDF	http://arxiv.org/pdf/1707.01058v2.pdf
PWC	https://paperswithcode.com/paper/skeleton-aided-articulated-motion-generation
Repo
Framework