October 17, 2019

2768 words 13 mins read

Paper Group ANR 867

Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review. Blind Justice: Fairness with Encrypted Sensitive Attributes. Fast and Sample Near-Optimal Algorithms for Learning Multidimensional Histograms. Motion Selective Prediction for Video Frame Synthesis. Efficient Uncertainty Estimation for Semantic Segmentation in Videos …

Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review


Title	Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
Authors	Sergey Levine
Abstract	The framework of reinforcement learning or optimal control provides a mathematical formalization of intelligent decision making that is powerful and broadly applicable. While the general form of the reinforcement learning problem enables effective reasoning about uncertainty, the connection between reinforcement learning and inference in probabilistic models is not immediately obvious. However, such a connection has considerable value when it comes to algorithm design: formalizing a problem as probabilistic inference in principle allows us to bring to bear a wide array of approximate inference tools, extend the model in flexible and powerful ways, and reason about compositionality and partial observability. In this article, we will discuss how a generalization of the reinforcement learning or optimal control problem, which is sometimes termed maximum entropy reinforcement learning, is equivalent to exact probabilistic inference in the case of deterministic dynamics, and variational inference in the case of stochastic dynamics. We will present a detailed derivation of this framework, overview prior work that has drawn on this and related ideas to propose new reinforcement learning and control algorithms, and describe perspectives on future research.
Tasks	Decision Making
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00909v3
PDF	http://arxiv.org/pdf/1805.00909v3.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-and-control-as
Repo
Framework


Title	Blind Justice: Fairness with Encrypted Sensitive Attributes
Authors	Niki Kilbertus, Adrià Gascón, Matt J. Kusner, Michael Veale, Krishna P. Gummadi, Adrian Weller
Abstract	Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes should not be considered. On the other hand, in order to avoid disparate impact, sensitive attributes must be examined, e.g., in order to learn a fair model, or to check if a given model is fair. We introduce methods from secure multi-party computation which allow us to avoid both. By encrypting sensitive attributes, we show how an outcome-based fair model may be learned, checked, or have its outputs verified and held to account, without users revealing their sensitive attributes.
Tasks
Published	2018-06-08
URL	http://arxiv.org/abs/1806.03281v1
PDF	http://arxiv.org/pdf/1806.03281v1.pdf
PWC	https://paperswithcode.com/paper/blind-justice-fairness-with-encrypted
Repo
Framework

Fast and Sample Near-Optimal Algorithms for Learning Multidimensional Histograms


Title	Fast and Sample Near-Optimal Algorithms for Learning Multidimensional Histograms
Authors	Ilias Diakonikolas, Jerry Li, Ludwig Schmidt
Abstract	We study the problem of robustly learning multi-dimensional histograms. A $d$-dimensional function $h: D \rightarrow \mathbb{R}$ is called a $k$-histogram if there exists a partition of the domain $D \subseteq \mathbb{R}^d$ into $k$ axis-aligned rectangles such that $h$ is constant within each such rectangle. Let $f: D \rightarrow \mathbb{R}$ be a $d$-dimensional probability density function and suppose that $f$ is $\mathrm{OPT}$-close, in $L_1$-distance, to an unknown $k$-histogram (with unknown partition). Our goal is to output a hypothesis that is $O(\mathrm{OPT}) + \epsilon$ close to $f$, in $L_1$-distance. We give an algorithm for this learning problem that uses $n = \tilde{O}_d(k/\epsilon^2)$ samples and runs in time $\tilde{O}_d(n)$. For any fixed dimension, our algorithm has optimal sample complexity, up to logarithmic factors, and runs in near-linear time. Prior to our work, the time complexity of the $d=1$ case was well-understood, but significant gaps in our understanding remained even for $d=2$.
Tasks
Published	2018-02-23
URL	http://arxiv.org/abs/1802.08513v1
PDF	http://arxiv.org/pdf/1802.08513v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-sample-near-optimal-algorithms-for
Repo
Framework

Motion Selective Prediction for Video Frame Synthesis


Title	Motion Selective Prediction for Video Frame Synthesis
Authors	Veronique Prinet
Abstract	Existing conditional video prediction approaches train a network from large databases and generalize to previously unseen data. We take the opposite stance, and introduce a model that learns from the first frames of a given video and extends its content and motion, to, eg, double its length. To this end, we propose a dual network that can use in a flexible way both dynamic and static convolutional motion kernels, to predict future frames. The construct of our model gives us the the means to efficiently analyze its functioning and interpret its output. We demonstrate experimentally the robustness of our approach on challenging videos in-the-wild and show that it is competitive wrt related baselines.
Tasks	Video Prediction
Published	2018-12-25
URL	http://arxiv.org/abs/1812.10157v1
PDF	http://arxiv.org/pdf/1812.10157v1.pdf
PWC	https://paperswithcode.com/paper/motion-selective-prediction-for-video-frame
Repo
Framework

Efficient Uncertainty Estimation for Semantic Segmentation in Videos


Title	Efficient Uncertainty Estimation for Semantic Segmentation in Videos
Authors	Po-Yu Huang, Wan-Ting Hsu, Chun-Yueh Chiu, Ting-Fan Wu, Min Sun
Abstract	Uncertainty estimation in deep learning becomes more important recently. A deep learning model can’t be applied in real applications if we don’t know whether the model is certain about the decision or not. Some literature proposes the Bayesian neural network which can estimate the uncertainty by Monte Carlo Dropout (MC dropout). However, MC dropout needs to forward the model $N$ times which results in $N$ times slower. For real-time applications such as a self-driving car system, which needs to obtain the prediction and the uncertainty as fast as possible, so that MC dropout becomes impractical. In this work, we propose the region-based temporal aggregation (RTA) method which leverages the temporal information in videos to simulate the sampling procedure. Our RTA method with Tiramisu backbone is 10x faster than the MC dropout with Tiramisu backbone ($N=5$). Furthermore, the uncertainty estimation obtained by our RTA method is comparable to MC dropout’s uncertainty estimation on pixel-level and frame-level metrics.
Tasks	Semantic Segmentation
Published	2018-07-29
URL	http://arxiv.org/abs/1807.11037v1
PDF	http://arxiv.org/pdf/1807.11037v1.pdf
PWC	https://paperswithcode.com/paper/efficient-uncertainty-estimation-for-semantic
Repo
Framework

Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks


Title	Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks
Authors	Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, Youngjin Yoon, In So Kweon
Abstract	Human behavior understanding is arguably one of the most important mid-level components in artificial intelligence. In order to efficiently make use of data, multi-task learning has been studied in diverse computer vision tasks including human behavior understanding. However, multi-task learning relies on task specific datasets and constructing such datasets can be cumbersome. It requires huge amounts of data, labeling efforts, statistical consideration etc. In this paper, we leverage existing single-task datasets for human action classification and captioning data for efficient human behavior learning. Since the data in each dataset has respective heterogeneous annotations, traditional multi-task learning is not effective in this scenario. To this end, we propose a novel alternating directional optimization method to efficiently learn from the heterogeneous data. We demonstrate the effectiveness of our model and show performance improvements on both classification and sentence retrieval tasks in comparison to the models trained on each of the single-task datasets.
Tasks	Action Classification, Multi-Task Learning
Published	2018-02-14
URL	http://arxiv.org/abs/1802.04962v1
PDF	http://arxiv.org/pdf/1802.04962v1.pdf
PWC	https://paperswithcode.com/paper/disjoint-multi-task-learning-between
Repo
Framework

Approximate Ranking from Pairwise Comparisons


Title	Approximate Ranking from Pairwise Comparisons
Authors	Reinhard Heckel, Max Simchowitz, Kannan Ramchandran, Martin J. Wainwright
Abstract	A common problem in machine learning is to rank a set of n items based on pairwise comparisons. Here ranking refers to partitioning the items into sets of pre-specified sizes according to their scores, which includes identification of the top-k items as the most prominent special case. The score of a given item is defined as the probability that it beats a randomly chosen other item. Finding an exact ranking typically requires a prohibitively large number of comparisons, but in practice, approximate rankings are often adequate. Accordingly, we study the problem of finding approximate rankings from pairwise comparisons. We analyze an active ranking algorithm that counts the number of comparisons won, and decides whether to stop or which pair of items to compare next, based on confidence intervals computed from the data collected in previous steps. We show that this algorithm succeeds in recovering approximate rankings using a number of comparisons that is close to optimal up to logarithmic factors. We also present numerical results, showing that in practice, approximation can drastically reduce the number of comparisons required to estimate a ranking.
Tasks
Published	2018-01-04
URL	http://arxiv.org/abs/1801.01253v1
PDF	http://arxiv.org/pdf/1801.01253v1.pdf
PWC	https://paperswithcode.com/paper/approximate-ranking-from-pairwise-comparisons
Repo
Framework

Expressing Linear Orders Requires Exponential-Size DNNFs


Title	Expressing Linear Orders Requires Exponential-Size DNNFs
Authors	Ronald de Haan
Abstract	We show that any DNNF circuit that expresses the set of linear orders over a set of $n$ candidates must be of size $2^{\Omega(n)}$. Moreover, we show that there exist DNNF circuits of size $2^{O(n)}$ expressing linear orders over $n$ candidates.
Tasks
Published	2018-07-17
URL	https://arxiv.org/abs/1807.06397v3
PDF	https://arxiv.org/pdf/1807.06397v3.pdf
PWC	https://paperswithcode.com/paper/expressing-linear-orders-requires-exponential
Repo
Framework

Dynamic Sparse Graph for Efficient Deep Learning


Title	Dynamic Sparse Graph for Efficient Deep Learning
Authors	Liu Liu, Lei Deng, Xing Hu, Maohua Zhu, Guoqi Li, Yufei Ding, Yuan Xie
Abstract	We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference. The great success of DNNs motivates the pursuing of lightweight models for the deployment onto embedded devices. However, most of the previous studies optimize for inference while neglect training or even complicate it. Training is far more intractable, since (i) the neurons dominate the memory cost rather than the weights in inference; (ii) the dynamic activation makes previous sparse acceleration via one-off optimization on fixed weight invalid; (iii) batch normalization (BN) is critical for maintaining accuracy while its activation reorganization damages the sparsity. To address these issues, DSG activates only a small amount of neurons with high selectivity at each iteration via a dimension-reduction search (DRS) and obtains the BN compatibility via a double-mask selection (DMS). Experiments show significant memory saving (1.7-4.5x) and operation reduction (2.3-4.4x) with little accuracy loss on various benchmarks.
Tasks	Dimensionality Reduction
Published	2018-10-01
URL	https://arxiv.org/abs/1810.00859v2
PDF	https://arxiv.org/pdf/1810.00859v2.pdf
PWC	https://paperswithcode.com/paper/dynamic-sparse-graph-for-efficient-deep
Repo
Framework

A neural network to classify metaphorical violence on cable news


Title	A neural network to classify metaphorical violence on cable news
Authors	Matthew A. Turner
Abstract	I present here an experimental system for identifying and annotating metaphor in corpora. It is designed to plug in to Metacorps, an experimental web app for annotating metaphor. As Metacorps users annotate metaphors, the system will use user annotations as training data. When the system is confident, it will suggest an identification and an annotation. Once approved by the user, this becomes more training data. This naturally allows for transfer learning, where the system can, with some known degree of reliability, classify one class of metaphor after only being trained on another class of metaphor. For example, in our metaphorical violence project, metaphors may be classified by the network they were observed on, the grammatical subject or object of the violence metaphor, or the violent word used (hit, attack, beat, etc.).
Tasks	Transfer Learning
Published	2018-10-19
URL	http://arxiv.org/abs/1810.08677v1
PDF	http://arxiv.org/pdf/1810.08677v1.pdf
PWC	https://paperswithcode.com/paper/a-neural-network-to-classify-metaphorical
Repo
Framework

Performance Metric Elicitation from Pairwise Classifier Comparisons


Title	Performance Metric Elicitation from Pairwise Classifier Comparisons
Authors	Gaurush Hiranandani, Shant Boodaghians, Ruta Mehta, Oluwasanmi Koyejo
Abstract	Given a binary prediction problem, which performance metric should the classifier optimize? We address this question by formalizing the problem of Metric Elicitation. The goal of metric elicitation is to discover the performance metric of a practitioner, which reflects her innate rewards (costs) for correct (incorrect) classification. In particular, we focus on eliciting binary classification performance metrics from pairwise feedback, where a practitioner is queried to provide relative preference between two classifiers. By exploiting key geometric properties of the space of confusion matrices, we obtain provably query efficient algorithms for eliciting linear and linear-fractional performance metrics. We further show that our method is robust to feedback and finite sample noise.
Tasks
Published	2018-06-05
URL	http://arxiv.org/abs/1806.01827v2
PDF	http://arxiv.org/pdf/1806.01827v2.pdf
PWC	https://paperswithcode.com/paper/performance-metric-elicitation-from-pairwise
Repo
Framework

Multi-Estimator Full Left Ventricle Quantification through Ensemble Learning


Title	Multi-Estimator Full Left Ventricle Quantification through Ensemble Learning
Authors	Jiasha Liu, Xiang Li, Hui Ren, Quanzheng Li
Abstract	Cardiovascular disease accounts for 1 in every 4 deaths in United States. Accurate estimation of structural and functional cardiac parameters is crucial for both diagnosis and disease management. In this work, we develop an ensemble learning framework for more accurate and robust left ventricle (LV) quantification. The framework combines two 1st-level modules: direct estimation module and a segmentation module. The direct estimation module utilizes Convolutional Neural Network (CNN) to achieve end-to-end quantification. The CNN is trained by taking 2D cardiac images as input and cardiac parameters as output. The segmentation module utilizes a U-Net architecture for obtaining pixel-wise prediction of the epicardium and endocardium of LV from the background. The binary U-Net output is then analyzed by a separate CNN for estimating the cardiac parameters. We then employ linear regression between the 1st-level predictor and ground truth to learn a 2nd-level predictor that ensembles the results from 1st-level modules for the final estimation. Preliminary results by testing the proposed framework on the LVQuan18 dataset show superior performance of the ensemble learning model over the two base modules.
Tasks
Published	2018-08-06
URL	http://arxiv.org/abs/1808.02056v1
PDF	http://arxiv.org/pdf/1808.02056v1.pdf
PWC	https://paperswithcode.com/paper/multi-estimator-full-left-ventricle
Repo
Framework


Title	Deep Learning on Operational Facility Data Related to Large-Scale Distributed Area Scientific Workflows
Authors	Alok Singh, Eric Stephan, Malachi Schram, Ilkay Altintas
Abstract	Distributed computing platforms provide a robust mechanism to perform large-scale computations by splitting the task and data among multiple locations, possibly located thousands of miles apart geographically. Although such distribution of resources can lead to benefits, it also comes with its associated problems such as rampant duplication of file transfers increasing congestion, long job completion times, unexpected site crashing, suboptimal data transfer rates, unpredictable reliability in a time range, and suboptimal usage of storage elements. In addition, each sub-system becomes a potential failure node that can trigger system wide disruptions. In this vision paper, we outline our approach to leveraging Deep Learning algorithms to discover solutions to unique problems that arise in a system with computational infrastructure that is spread over a wide area. The presented vision, motivated by a real scientific use case from Belle II experiments, is to develop multilayer neural networks to tackle forecasting, anomaly detection and optimization challenges in a complex and distributed data movement environment. Through this vision based on Deep Learning principles, we aim to achieve reduced congestion events, faster file transfer rates, and enhanced site reliability.
Tasks	Anomaly Detection
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06062v2
PDF	http://arxiv.org/pdf/1804.06062v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-on-operational-facility-data
Repo
Framework

A Broader View on Bias in Automated Decision-Making: Reflecting on Epistemology and Dynamics


Title	A Broader View on Bias in Automated Decision-Making: Reflecting on Epistemology and Dynamics
Authors	Roel Dobbe, Sarah Dean, Thomas Gilbert, Nitin Kohli
Abstract	Machine learning (ML) is increasingly deployed in real world contexts, supplying actionable insights and forming the basis of automated decision-making systems. While issues resulting from biases pre-existing in training data have been at the center of the fairness debate, these systems are also affected by technical and emergent biases, which often arise as context-specific artifacts of implementation. This position paper interprets technical bias as an epistemological problem and emergent bias as a dynamical feedback phenomenon. In order to stimulate debate on how to change machine learning practice to effectively address these issues, we explore this broader view on bias, stress the need to reflect on epistemology, and point to value-sensitive design methodologies to revisit the design and implementation process of automated decision-making systems.
Tasks	Decision Making
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00553v2
PDF	http://arxiv.org/pdf/1807.00553v2.pdf
PWC	https://paperswithcode.com/paper/a-broader-view-on-bias-in-automated-decision
Repo
Framework

Angry or Climbing Stairs? Towards Physiological Emotion Recognition in the Wild


Title	Angry or Climbing Stairs? Towards Physiological Emotion Recognition in the Wild
Authors	Judith S. Heinisch, Christoph Anderson, Klaus David
Abstract	Inferring emotions from physiological signals has gained much traction in the last years. Physiological responses to emotions, however, are commonly interfered and overlapped by physical activities, posing a challenge towards emotion recognition in the wild. In this paper, we address this challenge by investigating new features and machine-learning models for emotion recognition, non-sensitive to physical-based interferences. We recorded physiological signals from 18 participants that were exposed to emotions before and while performing physical activities to assess the performance of non-sensitive emotion recognition models. We trained models with the least exhaustive physical activity (sitting) and tested with the remaining, more exhausting activities. For three different emotion categories, we achieve classification accuracies ranging from 47.88% - 73.35% for selected feature sets and per participant. Furthermore, we investigate the performance across all participants and of each activity individually. In this regard, we achieve similar results, between 55.17% and 67.41%, indicating the viability of emotion recognition models not being influenced by single physical activities.
Tasks	Emotion Recognition
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04631v1
PDF	http://arxiv.org/pdf/1811.04631v1.pdf
PWC	https://paperswithcode.com/paper/angry-or-climbing-stairs-towards
Repo
Framework