January 27, 2020

3292 words 16 mins read

Paper Group ANR 1317

Localized Trajectories for 2D and 3D Action Recognition. A Regression Framework for Predicting User’s Next Location using Call Detail Records. Task-Driven Common Representation Learning via Bridge Neural Network. We Know Where We Don’t Know: 3D Bayesian CNNs for Uncertainty Quantification of Binary Segmentations for Material Simulations. Safe-Bayes …

Localized Trajectories for 2D and 3D Action Recognition


Title	Localized Trajectories for 2D and 3D Action Recognition
Authors	Konstantinos Papadopoulos, Girum Demisse, Enjie Ghorbel, Michel Antunes, Djamila Aouada, Björn Ottersten
Abstract	The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion, many generated trajectories are irrelevant to the actual human activity and can potentially lead to performance degradation. In this paper, we propose Localized Trajectories as an improved version of Dense Trajectories where motion trajectories are clustered around human body joints provided by RGB-D cameras and then encoded by local Bag-of-Words. As a result, the Localized Trajectories concept provides a more discriminative representation of actions as compared to Dense Trajectories. Moreover, we generalize Localized Trajectories to 3D by using the modalities offered by RGB-D cameras. One of the main advantages of using RGB-D data to generate trajectories is that they include radial displacements that are perpendicular to the image plane. Extensive experiments and analysis are carried out on five different datasets.
Tasks	3D Human Action Recognition, Temporal Action Localization
Published	2019-04-10
URL	http://arxiv.org/abs/1904.05244v1
PDF	http://arxiv.org/pdf/1904.05244v1.pdf
PWC	https://paperswithcode.com/paper/localized-trajectories-for-2d-and-3d-action
Repo
Framework

A Regression Framework for Predicting User’s Next Location using Call Detail Records


Title	A Regression Framework for Predicting User’s Next Location using Call Detail Records
Authors	Mohammad Saleh Mahdizadeh, Behnam Bahrak
Abstract	With the growth of using cell phones and the increase in diversity of smart mobile devices, a massive volume of data is generated continuously in the process of using these devices. Among these data, Call Detail Records, CDR, is highly remarkable. Since CDR contains both temporal and spatial labels, mobility analysis of CDR is one of the favorite subjects of study among the researchers. The user next location prediction is one of the main problems in the field of human mobility analysis. In this paper, we propose a data processing framework to predict user next location. We propose domain-specific data processing strategies and design a deep neural network model which is based on recurrent neurons and perform regression tasks. Using this prediction framework, the error of the prediction decreases from 74% to 55% in comparison to the worst and best performing traditional models. Methods, strategies, the framework and the results of this paper can be helpful in many applications such as urban planning and digital marketing.
Tasks
Published	2019-12-22
URL	https://arxiv.org/abs/1912.10438v1
PDF	https://arxiv.org/pdf/1912.10438v1.pdf
PWC	https://paperswithcode.com/paper/a-regression-framework-for-predicting-users
Repo
Framework

Task-Driven Common Representation Learning via Bridge Neural Network


Title	Task-Driven Common Representation Learning via Bridge Neural Network
Authors	Yao Xu, Xueshuang Xiang, Meiyu Huang
Abstract	This paper introduces a novel deep learning based method, named bridge neural network (BNN) to dig the potential relationship between two given data sources task by task. The proposed approach employs two convolutional neural networks that project the two data sources into a feature space to learn the desired common representation required by the specific task. The training objective with artificial negative samples is introduced with the ability of mini-batch training and it’s asymptotically equivalent to maximizing the total correlation of the two data sources, which is verified by the theoretical analysis. The experiments on the tasks, including pair matching, canonical correlation analysis, transfer learning, and reconstruction demonstrate the state-of-the-art performance of BNN, which may provide new insights into the aspect of common representation learning.
Tasks	Representation Learning, Transfer Learning
Published	2019-06-26
URL	https://arxiv.org/abs/1906.10897v1
PDF	https://arxiv.org/pdf/1906.10897v1.pdf
PWC	https://paperswithcode.com/paper/task-driven-common-representation-learning
Repo
Framework

We Know Where We Don’t Know: 3D Bayesian CNNs for Uncertainty Quantification of Binary Segmentations for Material Simulations


Title	We Know Where We Don’t Know: 3D Bayesian CNNs for Uncertainty Quantification of Binary Segmentations for Material Simulations
Authors	Tyler LaBonte, Carianne Martinez, Scott A. Roberts
Abstract	Deep learning has been applied with great success to the segmentation of 3D X-Ray Computed Tomography (CT) scans. Establishing the credibility of these segmentations requires uncertainty quantification (UQ) to identify problem areas. Recent UQ architectures include Monte Carlo dropout networks (MCDNs), which approximate Bayesian inference in deep Gaussian processes, and Bayesian neural networks (BNNs), which use variational inference to learn the posterior distribution of the neural network weights. BNNs hold several advantages over MCDNs for UQ, but due to the difficulty of training BNNs, they have not, to our knowledge, been successfully applied to 3D domains. In light of several recent developments in the implementation of BNNs, we present a novel 3D Bayesian convolutional neural network (BCNN) that provides accurate binary segmentations and uncertainty maps for 3D volumes. We present experimental results on CT scans of lithium-ion battery electrode materials and laser-welded metals to demonstrate that our BCNN provides improved UQ as compared to an MCDN while achieving equal or better segmentation accuracy. In particular, the uncertainty maps generated by our BCNN capture continuity and visual gradients, making them interpretable as confidence intervals for segmentation usable in subsequent simulations.
Tasks	Bayesian Inference, Computed Tomography (CT), Gaussian Processes
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10793v1
PDF	https://arxiv.org/pdf/1910.10793v1.pdf
PWC	https://paperswithcode.com/paper/we-know-where-we-dont-know-3d-bayesian-cnns
Repo
Framework

Safe-Bayesian Generalized Linear Regression


Title	Safe-Bayesian Generalized Linear Regression
Authors	Rianne de Heide, Alisa Kirichenko, Nishant Mehta, Peter Grünwald
Abstract	We study generalized Bayesian inference under misspecification, i.e. when the model is `wrong but useful’. Generalized Bayes equips the likelihood with a learning rate $\eta$. We show that for generalized linear models (GLMs), $\eta$-generalized Bayes concentrates around the best approximation of the truth within the model for specific $\eta \neq 1$, even under severely misspecified noise, as long as the tails of the true distribution are exponential. We then derive MCMC samplers for generalized Bayesian lasso and logistic regression, and give examples of both simulated and real-world data in which generalized Bayes outperforms standard Bayes by a vast margin. \|
Tasks	Bayesian Inference
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09227v1
PDF	https://arxiv.org/pdf/1910.09227v1.pdf
PWC	https://paperswithcode.com/paper/safe-bayesian-generalized-linear-regression
Repo
Framework

Stochastic triangular mesh mapping: A terrain mapping technique for autonomous mobile robots


Title	Stochastic triangular mesh mapping: A terrain mapping technique for autonomous mobile robots
Authors	Clint D. Lombard, Corné E. van Daalen
Abstract	For mobile robots to operate autonomously in general environments, perception is required in the form of a dense metric map. For this purpose, we present the stochastic triangular mesh (STM) mapping technique: a 2.5-D representation of the surface of the environment using a continuous mesh of triangular surface elements, where each surface element models the mean plane and roughness of the underlying surface. In contrast to existing mapping techniques, a STM map models the structure of the environment by ensuring a continuous model, while also being able to be incrementally updated with linear computational cost in the number of measurements. We reduce the effect of uncertainty in the robot pose (position and orientation) by using landmark-relative submaps. The uncertainty in the measurements and robot pose are accounted for by the use of Bayesian inference techniques during the map update. We demonstrate that a STM map can be used with sensors that generate point measurements, such as light detection and ranging (LiDAR) sensors and stereo cameras. We show that a STM map is a more accurate model than the only comparable online surface mapping technique$\unicode{x2014}$a standard elevation map$\unicode{x2014}$and we also provide qualitative results on practical datasets.
Tasks	Bayesian Inference
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03644v2
PDF	https://arxiv.org/pdf/1910.03644v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-triangular-mesh-mapping
Repo
Framework

Evaluating Scalable Uncertainty Estimation Methods for DNN-Based Molecular Property Prediction


Title	Evaluating Scalable Uncertainty Estimation Methods for DNN-Based Molecular Property Prediction
Authors	Gabriele Scalia, Colin A. Grambow, Barbara Pernici, Yi-Pei Li, William H. Green
Abstract	Advances in deep neural network (DNN) based molecular property prediction have recently led to the development of models of remarkable accuracy and generalization ability, with graph convolution neural networks (GCNNs) reporting state-of-the-art performance for this task. However, some challenges remain and one of the most important that needs to be fully addressed concerns uncertainty quantification. DNN performance is affected by the volume and the quality of the training samples. Therefore, establishing when and to what extent a prediction can be considered reliable is just as important as outputting accurate predictions, especially when out-of-domain molecules are targeted. Recently, several methods to account for uncertainty in DNNs have been proposed, most of which are based on approximate Bayesian inference. Among these, only a few scale to the large datasets required in applications. Evaluating and comparing these methods has recently attracted great interest, but results are generally fragmented and absent for molecular property prediction. In this paper, we aim to quantitatively compare scalable techniques for uncertainty estimation in GCNNs. We introduce a set of quantitative criteria to capture different uncertainty aspects, and then use these criteria to compare MC-Dropout, deep ensembles, and bootstrapping, both theoretically in a unified framework that separates aleatoric/epistemic uncertainty and experimentally on the QM9 dataset. Our experiments quantify the performance of the different uncertainty estimation methods and their impact on uncertainty-related error reduction. Our findings indicate that ensembling and bootstrapping consistently outperform MC-Dropout, with different context-specific pros and cons. Our analysis also leads to a better understanding of the role of aleatoric/epistemic uncertainty and highlights the challenge posed by out-of-domain uncertainty.
Tasks	Bayesian Inference, Molecular Property Prediction
Published	2019-10-07
URL	https://arxiv.org/abs/1910.03127v1
PDF	https://arxiv.org/pdf/1910.03127v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-scalable-uncertainty-estimation
Repo
Framework

DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow


Title	DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow
Authors	Xiang Pan, Tianyu Zhao, Minghua Chen
Abstract	We develop DeepOPF as a Deep Neural Network (DNN) approach for solving security-constrained direct current optimal power flow (SC-DCOPF) problems, which are critical for reliable and cost-effective power system operation. DeepOPF is inspired by the observation that solving the SC-DCOPF problem for a given power network is equivalent to depicting a high-dimensional mapping between load inputs and generation and phase-angle outputs. We first construct and train a DNN to learn the mapping between the load inputs and the generations. We then directly compute the phase angles from the generations and loads by using the (linearized) power flow equations. Such a two-step procedure significantly reduces the dimension of the mapping to learn, subsequently cutting down the size of the DNN and the amount of training data/time needed. We further characterize a condition that allows us to tune the size of our neural network according to the desired approximation accuracy of the load-to-generation mapping. Simulation results of IEEE test cases show that DeepOPF always generates feasible solutions with negligible optimality loss, while speeding up the computing time by up to 400x as compared to a state-of-the-art solver.
Tasks
Published	2019-10-30
URL	https://arxiv.org/abs/1910.14448v1
PDF	https://arxiv.org/pdf/1910.14448v1.pdf
PWC	https://paperswithcode.com/paper/deepopf-a-deep-neural-network-approach-for
Repo
Framework

A framework for deep energy-based reinforcement learning with quantum speed-up


Title	A framework for deep energy-based reinforcement learning with quantum speed-up
Authors	Sofiene Jerbi, Hendrik Poulsen Nautrup, Lea M. Trenkwalder, Hans J. Briegel, Vedran Dunjko
Abstract	In the past decade, deep learning methods have seen tremendous success in various supervised and unsupervised learning tasks such as classification and generative modeling. More recently, deep neural networks have emerged in the domain of reinforcement learning as a tool to solve decision-making problems of unprecedented complexity, e.g., navigation problems or game-playing AI. Despite the successful combinations of ideas from quantum computing with machine learning methods, there have been relatively few attempts to design quantum algorithms that would enhance deep reinforcement learning. This is partly due to the fact that quantum enhancements of deep neural networks, in general, have not been as extensively investigated as other quantum machine learning methods. In contrast, projective simulation is a reinforcement learning model inspired by the stochastic evolution of physical systems that enables a quantum speed-up in decision making. In this paper, we develop a unifying framework that connects deep learning and projective simulation, opening the route to quantum improvements in deep reinforcement learning. Our approach is based on so-called generative energy-based models to design reinforcement learning methods with a computational advantage in solving complex and large-scale decision-making problems.
Tasks	Decision Making, Quantum Machine Learning
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12760v1
PDF	https://arxiv.org/pdf/1910.12760v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-deep-energy-based
Repo
Framework

Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimization


Title	Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimization
Authors	Ying Zhang, Ömer Deniz Akyildiz, Theodoros Damoulas, Sotirios Sabanis
Abstract	Within the context of empirical risk minimization, see Raginsky, Rakhlin, and Telgarsky (2017), we are concerned with a non-asymptotic analysis of sampling algorithms used in optimization. In particular, we obtain non-asymptotic error bounds for a popular class of algorithms called Stochastic Gradient Langevin Dynamics (SGLD). These results are derived in Wasserstein-1 and Wasserstein-2 distances in the absence of log-concavity of the target distribution. More precisely, the stochastic gradient $H(\theta, x)$ is assumed to be locally Lipschitz continuous in both variables, and furthermore, the dissipativity condition is relaxed by removing its uniform dependence in $x$. This relaxation allows us to present two key paradigms within the framework of scalable posterior sampling for Bayesian inference and of nonconvex optimization; namely, examples from minibatch logistic regression and from variational inference are given by providing theoretical guarantees for the sampling behaviour of the algorithm.
Tasks	Bayesian Inference
Published	2019-10-04
URL	https://arxiv.org/abs/1910.02008v3
PDF	https://arxiv.org/pdf/1910.02008v3.pdf
PWC	https://paperswithcode.com/paper/nonasymptotic-estimates-for-stochastic
Repo
Framework

A Deep Learning based approach to VM behavior identification in cloud systems


Title	A Deep Learning based approach to VM behavior identification in cloud systems
Authors	Matteo Stefanini, Riccardo Lancellotti, Lorenzo Baraldi, Simone Calderara
Abstract	Cloud computing data centers are growing in size and complexity to the point where monitoring and management of the infrastructure become a challenge due to scalability issues. A possible approach to cope with the size of such data centers is to identify VMs exhibiting a similar behavior. Existing literature demonstrated that clustering together VMs that show a similar behavior may improve the scalability of both monitoring andmanagement of a data center. However, available techniques suffer from a trade-off between accuracy and time to achieve this result. Throughout this paper we propose a different approach where, instead of an unsupervised clustering, we rely on classifiers based on deep learning techniques to assigna newly deployed VMs to a cluster of already-known VMs. The two proposed classifiers, namely DeepConv and DeepFFT use a convolution neural network and (in the latter model) exploits Fast Fourier Transformation to classify the VMs. Our proposal is validated using a set of traces describing the behavior of VMs from a realcloud data center. The experiments compare our proposal with state-of-the-art solutions available in literature, demonstrating that our proposal achieve better performance. Furthermore, we show that our solution issignificantly faster than the alternatives as it can produce a perfect classification even with just a few samples of data, making our proposal viable also toclassify on-demand VMs that are characterized by a short life span.
Tasks
Published	2019-03-05
URL	http://arxiv.org/abs/1903.01930v1
PDF	http://arxiv.org/pdf/1903.01930v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-based-approach-to-vm-behavior
Repo
Framework

Multi-classifier prediction of knee osteoarthritis progression from incomplete imbalanced longitudinal data


Title	Multi-classifier prediction of knee osteoarthritis progression from incomplete imbalanced longitudinal data
Authors	Paweł Widera, Paco M. J. Welsing, Christoph Ladel, John Loughlin, Floris P. F. J. Lafeber, Florence Petit Dop, Jonathan Larkin, Harrie Weinans, Ali Mobasheri, Jaume Bacardit
Abstract	Conventional inclusion criteria used in osteoarthritis clinical trials are not very effective in selecting patients who would benefit the most from a therapy under test. Typically these criteria select majority of patients who show no or limited disease progression during a short evaluation window of the study. As a consequence, less insight on the relative effect of the treatment can be gained from the collected data, and the efforts and resources invested in running the study are not paying off. This could be avoided, if selection criteria were more predictive of the future disease progression. In this article, we formulated the patient selection problem as a multi-class classification task, with classes based on clinically relevant measures of progression (over a time scale typical for clinical trials). Using data from two long-term knee osteoarthritis studies OAI and CHECK, we tested multiple algorithms and learning process configurations (including multi-classifier approaches, cost-sensitive learning, and feature selection), to identify the best performing machine learning models. We examined the behaviour of the best models, with respect to prediction errors and the impact of used features, to confirm their clinical relevance. We found that the model-based selection outperforms the conventional inclusion criteria, reducing by 20-25% the number of patients who show no progression and making the representation of the patient categories more even. This result indicates that our machine learning approach could lead to efficiency improvements in clinical trial design.
Tasks	Feature Selection
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13408v1
PDF	https://arxiv.org/pdf/1909.13408v1.pdf
PWC	https://paperswithcode.com/paper/multi-classifier-prediction-of-knee
Repo
Framework

Shadow Removal via Shadow Image Decomposition


Title	Shadow Removal via Shadow Image Decomposition
Authors	Hieu Le, Dimitris Samaras
Abstract	We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks, namely SP-Net and M-Net, to predict the shadow parameters and the shadow matte respectively. This system allows us to remove the shadow effects on the images. We train and test our framework on the most challenging shadow removal dataset (ISTD). Compared to the state-of-the-art method, our model achieves a 40% error reduction in terms of root mean square error (RMSE) for the shadow area, reducing RMSE from 13.3 to 7.9. Moreover, we create an augmented ISTD dataset based on an image decomposition system by modifying the shadow parameters to generate new synthetic shadow images. Training our model on this new augmented ISTD dataset further lowers the RMSE on the shadow area to 7.4.
Tasks
Published	2019-08-23
URL	https://arxiv.org/abs/1908.08628v1
PDF	https://arxiv.org/pdf/1908.08628v1.pdf
PWC	https://paperswithcode.com/paper/shadow-removal-via-shadow-image-decomposition
Repo
Framework

The Implicit Regularization of Ordinary Least Squares Ensembles


Title	The Implicit Regularization of Ordinary Least Squares Ensembles
Authors	Daniel LeJeune, Hamid Javadi, Richard G. Baraniuk
Abstract	Ensemble methods that average over a collection of independent predictors that are each limited to a subsampling of both the examples and features of the training data command a significant presence in machine learning, such as the ever-popular random forest, yet the nature of the subsampling effect, particularly of the features, is not well understood. We study the case of an ensemble of linear predictors, where each individual predictor is fit using ordinary least squares on a random submatrix of the data matrix. We show that, under standard Gaussianity assumptions, when the number of features selected for each predictor is optimally tuned, the asymptotic risk of a large ensemble is equal to the asymptotic ridge regression risk, which is known to be optimal among linear predictors in this setting. In addition to eliciting this implicit regularization that results from subsampling, we also connect this ensemble to the dropout technique used in training deep (neural) networks, another strategy that has been shown to have a ridge-like regularizing effect.
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04743v2
PDF	https://arxiv.org/pdf/1910.04743v2.pdf
PWC	https://paperswithcode.com/paper/the-implicit-regularization-of-ordinary-least
Repo
Framework

Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Learning


Title	Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Learning
Authors	Huy N. Chau, Miklos Rasonyi
Abstract	Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) is a momentum version of stochastic gradient descent with properly injected Gaussian noise to find a global minimum. In this paper, non-asymptotic convergence analysis of SGHMC is given in the context of non-convex optimization, where subsampling techniques are used over an i.i.d dataset for gradient updates. Our results complement those of [RRT17] and improve on those of [GGZ18].
Tasks
Published	2019-03-25
URL	https://arxiv.org/abs/1903.10328v3
PDF	https://arxiv.org/pdf/1903.10328v3.pdf
PWC	https://paperswithcode.com/paper/stochastic-gradient-hamiltonian-monte-carlo-2
Repo
Framework