July 27, 2019

2980 words 14 mins read

Paper Group ANR 602

On-line Building Energy Optimization using Deep Reinforcement Learning. Sparse inference of the drift of a high-dimensional Ornstein-Uhlenbeck process. Hand3D: Hand Pose Estimation using 3D Neural Network. Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training. Visually-Aware Fashion Recommendation and Design with …

On-line Building Energy Optimization using Deep Reinforcement Learning


Title	On-line Building Energy Optimization using Deep Reinforcement Learning
Authors	Elena Mocanu, Decebal Constantin Mocanu, Phuong H. Nguyen, Antonio Liotta, Michael E. Webber, Madeleine Gibescu, J. G. Slootweg
Abstract	Unprecedented high volumes of data are becoming available with the growth of the advanced metering infrastructure. These are expected to benefit planning and operation of the future power system, and to help the customers transition from a passive to an active role. In this paper, we explore for the first time in the smart grid context the benefits of using Deep Reinforcement Learning, a hybrid type of methods that combines Reinforcement Learning with Deep Learning, to perform on-line optimization of schedules for building energy management systems. The learning procedure was explored using two methods, Deep Q-learning and Deep Policy Gradient, both of them being extended to perform multiple actions simultaneously. The proposed approach was validated on the large-scale Pecan Street Inc. database. This highly-dimensional database includes information about photovoltaic power generation, electric vehicles as well as buildings appliances. Moreover, these on-line energy scheduling strategies could be used to provide real-time feedback to consumers to encourage more efficient use of electricity.
Tasks	Q-Learning
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05878v1
PDF	http://arxiv.org/pdf/1707.05878v1.pdf
PWC	https://paperswithcode.com/paper/on-line-building-energy-optimization-using
Repo
Framework

Sparse inference of the drift of a high-dimensional Ornstein-Uhlenbeck process


Title	Sparse inference of the drift of a high-dimensional Ornstein-Uhlenbeck process
Authors	Stéphane Gaïffas, Gustaw Matulewicz
Abstract	Given the observation of a high-dimensional Ornstein-Uhlenbeck (OU) process in continuous time, we proceed to the inference of the drift parameter under a row-sparsity assumption. Towards that aim, we consider the negative log-likelihood of the process, penalized by an $\ell^1$-penalization (Lasso and Adaptive Lasso). We provide both non-asymptotic and asymptotic results for this procedure, by means of a sharp oracle inequality, and a limit theorem in the long-time asymptotics, including asymptotic consistency for variable selection. As a by-product, we point out the fact that for the Ornstein-Uhlenbeck process, one does not need an assumption of restricted eigenvalue type in order to derive fast rates for the Lasso, while it is well-known to be mandatory for linear regression for instance. Numerical results illustrate the benefits of this penalized procedure compared to standard maximum likelihood approaches both on simulations and real-world financial data.
Tasks
Published	2017-07-10
URL	http://arxiv.org/abs/1707.03010v1
PDF	http://arxiv.org/pdf/1707.03010v1.pdf
PWC	https://paperswithcode.com/paper/sparse-inference-of-the-drift-of-a-high
Repo
Framework

Hand3D: Hand Pose Estimation using 3D Neural Network


Title	Hand3D: Hand Pose Estimation using 3D Neural Network
Authors	Xiaoming Deng, Shuo Yang, Yinda Zhang, Ping Tan, Liang Chang, Hongan Wang
Abstract	We propose a novel 3D neural network architecture for 3D hand pose estimation from a single depth image. Different from previous works that mostly run on 2D depth image domain and require intermediate or post process to bring in the supervision from 3D space, we convert the depth map to a 3D volumetric representation, and feed it into a 3D convolutional neural network(CNN) to directly produce the pose in 3D requiring no further process. Our system does not require the ground truth reference point for initialization, and our network architecture naturally integrates both local feature and global context in 3D space. To increase the coverage of the hand pose space of the training data, we render synthetic depth image by transferring hand pose from existing real image datasets. We evaluation our algorithm on two public benchmarks and achieve the state-of-the-art performance. The synthetic hand pose dataset will be available.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02224v1
PDF	http://arxiv.org/pdf/1704.02224v1.pdf
PWC	https://paperswithcode.com/paper/hand3d-hand-pose-estimation-using-3d-neural
Repo
Framework

Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training


Title	Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Authors	Yujun Lin, Song Han, Huizi Mao, Yu Wang, William J. Dally
Abstract	Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure. The situation gets even worse with distributed training on mobile devices (federated learning), which suffers from higher latency, lower throughput, and intermittent poor connections. In this paper, we find 99.9% of the gradient exchange in distributed SGD is redundant, and propose Deep Gradient Compression (DGC) to greatly reduce the communication bandwidth. To preserve accuracy during compression, DGC employs four methods: momentum correction, local gradient clipping, momentum factor masking, and warm-up training. We have applied Deep Gradient Compression to image classification, speech recognition, and language modeling with multiple datasets including Cifar10, ImageNet, Penn Treebank, and Librispeech Corpus. On these scenarios, Deep Gradient Compression achieves a gradient compression ratio from 270x to 600x without losing accuracy, cutting the gradient size of ResNet-50 from 97MB to 0.35MB, and for DeepSpeech from 488MB to 0.74MB. Deep gradient compression enables large-scale distributed training on inexpensive commodity 1Gbps Ethernet and facilitates distributed training on mobile.
Tasks	Image Classification, Language Modelling, Speech Recognition
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01887v2
PDF	http://arxiv.org/pdf/1712.01887v2.pdf
PWC	https://paperswithcode.com/paper/deep-gradient-compression-reducing-the
Repo
Framework

Visually-Aware Fashion Recommendation and Design with Generative Image Models


Title	Visually-Aware Fashion Recommendation and Design with Generative Image Models
Authors	Wang-Cheng Kang, Chen Fang, Zhaowen Wang, Julian McAuley
Abstract	Building effective recommender systems for domains like fashion is challenging due to the high level of subjectivity and the semantic complexity of the features involved (i.e., fashion styles). Recent work has shown that approaches to `visual' recommendation (e.g.~clothing, art, etc.) can be made more accurate by incorporating visual signals directly into the recommendation objective, using` off-the-shelf’ feature representations derived from deep networks. Here, we seek to extend this contribution by showing that recommendation performance can be significantly improved by learning `fashion aware’ image representations directly, i.e., by training the image representation (from the pixel level) and the recommender system jointly; this contribution is related to recent work using Siamese CNNs, though we are able to show improvements over state-of-the-art recommendation techniques such as BPR and variants that make use of pre-trained visual features. Furthermore, we show that our model can be used \emph{generatively}, i.e., given a user and a product category, we can generate new images (i.e., clothing items) that are most consistent with their personal taste. This represents a first step towards building systems that go beyond recommending existing items from a product corpus, but which can be used to suggest styles and aid the design of new products. \|
Tasks	Recommendation Systems
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02231v1
PDF	http://arxiv.org/pdf/1711.02231v1.pdf
PWC	https://paperswithcode.com/paper/visually-aware-fashion-recommendation-and
Repo
Framework

Facies classification from well logs using an inception convolutional network


Title	Facies classification from well logs using an inception convolutional network
Authors	Valentin Tschannen, Matthias Delescluse, Mathieu Rodriguez, Janis Keuper
Abstract	The idea to use automated algorithms to determine geological facies from well logs is not new (see e.g Busch et al. (1987); Rabaute (1998)) but the recent and dramatic increase in research in the field of machine learning makes it a good time to revisit the topic. Following an exercise proposed by Dubois et al. (2007) and Hall (2016) we employ a modern type of deep convolutional network, called \textit{inception network} (Szegedy et al., 2015), to tackle the supervised classification task and we discuss the methodological limits of such problem as well as further research opportunities.
Tasks	Facies Classification
Published	2017-06-02
URL	http://arxiv.org/abs/1706.00613v1
PDF	http://arxiv.org/pdf/1706.00613v1.pdf
PWC	https://paperswithcode.com/paper/facies-classification-from-well-logs-using-an
Repo
Framework

OntoMath Digital Ecosystem: Ontologies, Mathematical Knowledge Analytics and Management


Title	OntoMath Digital Ecosystem: Ontologies, Mathematical Knowledge Analytics and Management
Authors	Alexander Elizarov, Alexander Kirillovich, Evgeny Lipachev, Olga Nevzorova
Abstract	In this article we consider the basic ideas, approaches and results of developing of mathematical knowledge management technologies based on ontologies. These solutions form the basis of a specialized digital ecosystem OntoMath which consists of the ontology of the logical structure of mathematical documents Mocassin and ontology of mathematical knowledge OntoMathPRO, tools of text analysis, recommender system and other applications to manage mathematical knowledge. The studies are in according to the ideas of creating a distributed system of interconnected repositories of digitized versions of mathematical documents and project to create a World Digital Mathematical Library.
Tasks	Recommendation Systems
Published	2017-02-16
URL	http://arxiv.org/abs/1702.05112v1
PDF	http://arxiv.org/pdf/1702.05112v1.pdf
PWC	https://paperswithcode.com/paper/ontomath-digital-ecosystem-ontologies
Repo
Framework

The Doctor Just Won’t Accept That!


Title	The Doctor Just Won’t Accept That!
Authors	Zachary C. Lipton
Abstract	Calls to arms to build interpretable models express a well-founded discomfort with machine learning. Should a software agent that does not even know what a loan is decide who qualifies for one? Indeed, we ought to be cautious about injecting machine learning (or anything else, for that matter) into applications where there may be a significant risk of causing social harm. However, claims that stakeholders “just won’t accept that!” do not provide a sufficient foundation for a proposed field of study. For the field of interpretable machine learning to advance, we must ask the following questions: What precisely won’t various stakeholders accept? What do they want? Are these desiderata reasonable? Are they feasible? In order to answer these questions, we’ll have to give real-world problems and their respective stakeholders greater consideration.
Tasks	Interpretable Machine Learning
Published	2017-11-20
URL	http://arxiv.org/abs/1711.08037v2
PDF	http://arxiv.org/pdf/1711.08037v2.pdf
PWC	https://paperswithcode.com/paper/the-doctor-just-wont-accept-that
Repo
Framework

Applications of Trajectory Data from the Perspective of a Road Transportation Agency: Literature Review and Maryland Case Study


Title	Applications of Trajectory Data from the Perspective of a Road Transportation Agency: Literature Review and Maryland Case Study
Authors	Nikola Marković, Przemysław Sekuła, Zachary Vander Laan, Gennady Andrienko, Natalia Andrienko
Abstract	Transportation agencies have an opportunity to leverage increasingly-available trajectory datasets to improve their analyses and decision-making processes. However, this data is typically purchased from vendors, which means agencies must understand its potential benefits beforehand in order to properly assess its value relative to the cost of acquisition. While the literature concerned with trajectory data is rich, it is naturally fragmented and focused on technical contributions in niche areas, which makes it difficult for government agencies to assess its value across different transportation domains. To overcome this issue, the current paper explores trajectory data from the perspective of a road transportation agency interested in acquiring trajectories to enhance its analyses. The paper provides a literature review illustrating applications of trajectory data in six areas of road transportation systems analysis: demand estimation, modeling human behavior, designing public transit, traffic performance measurement and prediction, environment and safety. In addition, it visually explores 20 million GPS traces in Maryland, illustrating existing and suggesting new applications of trajectory data.
Tasks	Decision Making
Published	2017-08-23
URL	http://arxiv.org/abs/1708.07193v2
PDF	http://arxiv.org/pdf/1708.07193v2.pdf
PWC	https://paperswithcode.com/paper/applications-of-trajectory-data-from-the
Repo
Framework

Complex Word Identification: Challenges in Data Annotation and System Performance


Title	Complex Word Identification: Challenges in Data Annotation and System Performance
Authors	Marcos Zampieri, Shervin Malmasi, Gustavo Paetzold, Lucia Specia
Abstract	This paper revisits the problem of complex word identification (CWI) following up the SemEval CWI shared task. We use ensemble classifiers to investigate how well computational methods can discriminate between complex and non-complex words. Furthermore, we analyze the classification performance to understand what makes lexical complexity challenging. Our findings show that most systems performed poorly on the SemEval CWI dataset, and one of the reasons for that is the way in which human annotation was performed.
Tasks	Complex Word Identification
Published	2017-10-13
URL	http://arxiv.org/abs/1710.04989v1
PDF	http://arxiv.org/pdf/1710.04989v1.pdf
PWC	https://paperswithcode.com/paper/complex-word-identification-challenges-in
Repo
Framework

MRI-PET Registration with Automated Algorithm in Pre-clinical Studies


Title	MRI-PET Registration with Automated Algorithm in Pre-clinical Studies
Authors	Nathanael L. Baisa, Stéphanie Bricq, Alain Lalande
Abstract	Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) automatic 3-D registration is implemented and validated for small animal image volumes so that the high-resolution anatomical MRI information can be fused with the low spatial resolution of functional PET information for the localization of lesion that is currently in high demand in the study of tumor of cancer (oncology) and its corresponding preparation of pharmaceutical drugs. Though many registration algorithms are developed and applied on human brain volumes, these methods may not be as efficient on small animal datasets due to lack of intensity information and often the high anisotropy in voxel dimensions. Therefore, a fully automatic registration algorithm which can register not only assumably rigid small animal volumes such as brain but also deformable organs such as kidney, cardiac and chest is developed using a combination of global affine and local B-spline transformation models in which mutual information is used as a similarity criterion. The global affine registration uses a multi-resolution pyramid on image volumes of 3 levels whereas in local B-spline registration, a multi-resolution scheme is applied on the B-spline grid of 2 levels on the finest resolution of the image volumes in which only the transform itself is affected rather than the image volumes. Since mutual information lacks sufficient spatial information, PCA is used to inject it by estimating initial translation and rotation parameters. It is computationally efficient since it is implemented using C++ and ITK library, and is qualitatively and quantitatively shown that this PCA-initialized global registration followed by local registration is in close agreement with expert manual registration and outperforms the one without PCA initialization tested on small animal brain and kidney.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07062v2
PDF	http://arxiv.org/pdf/1705.07062v2.pdf
PWC	https://paperswithcode.com/paper/mri-pet-registration-with-automated-algorithm
Repo
Framework

What Does a Belief Function Believe In ?


Title	What Does a Belief Function Believe In ?
Authors	Andrzej Matuszewski, Mieczysław A. Kłopotek
Abstract	The conditioning in the Dempster-Shafer Theory of Evidence has been defined (by Shafer \cite{Shafer:90} as combination of a belief function and of an “event” via Dempster rule. On the other hand Shafer \cite{Shafer:90} gives a “probabilistic” interpretation of a belief function (hence indirectly its derivation from a sample). Given the fact that conditional probability distribution of a sample-derived probability distribution is a probability distribution derived from a subsample (selected on the grounds of a conditioning event), the paper investigates the empirical nature of the Dempster- rule of combination. It is demonstrated that the so-called “conditional” belief function is not a belief function given an event but rather a belief function given manipulation of original empirical data.\ Given this, an interpretation of belief function different from that of Shafer is proposed. Algorithms for construction of belief networks from data are derived for this interpretation.
Tasks
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02686v1
PDF	http://arxiv.org/pdf/1706.02686v1.pdf
PWC	https://paperswithcode.com/paper/what-does-a-belief-function-believe-in
Repo
Framework

A hybrid exact-ACO algorithm for the joint scheduling, power and cluster assignment in cooperative wireless networks


Title	A hybrid exact-ACO algorithm for the joint scheduling, power and cluster assignment in cooperative wireless networks
Authors	Fabio D’Andreagiovanni
Abstract	Base station cooperation (BSC) has recently arisen as a promising way to increase the capacity of a wireless network. Implementing BSC adds a new design dimension to the classical wireless network design problem: how to define the subset of base stations (clusters) that coordinate to serve a user. Though the problem of forming clusters has been extensively discussed from a technical point of view, there is still a lack of effective optimization models for its representation and algorithms for its solution. In this work, we make a further step towards filling such gap: 1) we generalize the classical network design problem by adding cooperation as an additional decision dimension; 2) we develop a strong formulation for the resulting problem; 3) we define a new hybrid solution algorithm that combines exact large neighborhood search and ant colony optimization. Finally, we assess the performance of our new model and algorithm on a set of realistic instances of a WiMAX network.
Tasks
Published	2017-04-21
URL	http://arxiv.org/abs/1704.06684v1
PDF	http://arxiv.org/pdf/1704.06684v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-exact-aco-algorithm-for-the-joint
Repo
Framework

Observational Learning by Reinforcement Learning


Title	Observational Learning by Reinforcement Learning
Authors	Diana Borsa, Bilal Piot, Rémi Munos, Olivier Pietquin
Abstract	Observational learning is a type of learning that occurs as a function of observing, retaining and possibly replicating or imitating the behaviour of another agent. It is a core mechanism appearing in various instances of social learning and has been found to be employed in several intelligent species, including humans. In this paper, we investigate to what extent the explicit modelling of other agents is necessary to achieve observational learning through machine learning. Especially, we argue that observational learning can emerge from pure Reinforcement Learning (RL), potentially coupled with memory. Through simple scenarios, we demonstrate that an RL agent can leverage the information provided by the observations of an other agent performing a task in a shared environment. The other agent is only observed through the effect of its actions on the environment and never explicitly modeled. Two key aspects are borrowed from observational learning: i) the observer behaviour needs to change as a result of viewing a ‘teacher’ (another agent) and ii) the observer needs to be motivated somehow to engage in making use of the other agent’s behaviour. The later is naturally modeled by RL, by correlating the learning agent’s reward with the teacher agent’s behaviour.
Tasks
Published	2017-06-20
URL	http://arxiv.org/abs/1706.06617v1
PDF	http://arxiv.org/pdf/1706.06617v1.pdf
PWC	https://paperswithcode.com/paper/observational-learning-by-reinforcement
Repo
Framework

EE-Grad: Exploration and Exploitation for Cost-Efficient Mini-Batch SGD


Title	EE-Grad: Exploration and Exploitation for Cost-Efficient Mini-Batch SGD
Authors	Mehmet A. Donmez, Maxim Raginsky, Andrew C. Singer
Abstract	We present a generic framework for trading off fidelity and cost in computing stochastic gradients when the costs of acquiring stochastic gradients of different quality are not known a priori. We consider a mini-batch oracle that distributes a limited query budget over a number of stochastic gradients and aggregates them to estimate the true gradient. Since the optimal mini-batch size depends on the unknown cost-fidelity function, we propose an algorithm, {\it EE-Grad}, that sequentially explores the performance of mini-batch oracles and exploits the accumulated knowledge to estimate the one achieving the best performance in terms of cost-efficiency. We provide performance guarantees for EE-Grad with respect to the optimal mini-batch oracle, and illustrate these results in the case of strongly convex objectives. We also provide a simple numerical example that corroborates our theoretical findings.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07070v1
PDF	http://arxiv.org/pdf/1705.07070v1.pdf
PWC	https://paperswithcode.com/paper/ee-grad-exploration-and-exploitation-for-cost
Repo
Framework