January 28, 2020

3328 words 16 mins read

Paper Group ANR 913

Learning physics-based reduced-order models for a single-injector combustion process. Do not Omit Local Minimizer: a Complete Solution for Pose Estimation from 3D Correspondences. Are Out-of-Distribution Detection Methods Effective on Large-Scale Datasets?. Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning. Detecting Cyber …

Learning physics-based reduced-order models for a single-injector combustion process


Title	Learning physics-based reduced-order models for a single-injector combustion process
Authors	Renee Swischuk, Boris Kramer, Cheng Huang, Karen Willcox
Abstract	This paper presents a physics-based data-driven method to learn predictive reduced-order models (ROMs) from high-fidelity simulations, and illustrates it in the challenging context of a single-injector combustion process. The method combines the perspectives of model reduction and machine learning. Model reduction brings in the physics of the problem, constraining the ROM predictions to lie on a subspace defined by the governing equations. This is achieved by defining the ROM in proper orthogonal decomposition (POD) coordinates, which embed the rich physics information contained in solution snapshots of a high-fidelity computational fluid dynamics (CFD) model. The machine learning perspective brings the flexibility to use transformed physical variables to define the POD basis. This is in contrast to traditional model reduction approaches that are constrained to use the physical variables of the high-fidelity code. Combining the two perspectives, the approach identifies a set of transformed physical variables that expose quadratic structure in the combustion governing equations and learns a quadratic ROM from transformed snapshot data. This learning does not require access to the high-fidelity model implementation. Numerical experiments show that the ROM accurately predicts temperature, pressure, velocity, species concentrations, and the limit-cycle amplitude, with speedups of more than five orders of magnitude over high-fidelity models. Our ROM simulation is shown to be predictive 200% past the training interval. Moreover, ROM-predicted pressure traces accurately match the phase of the pressure signal and yield good approximations of the limit-cycle amplitude.
Tasks
Published	2019-08-09
URL	https://arxiv.org/abs/1908.03620v3
PDF	https://arxiv.org/pdf/1908.03620v3.pdf
PWC	https://paperswithcode.com/paper/learning-physics-based-reduced-order-models
Repo
Framework

Do not Omit Local Minimizer: a Complete Solution for Pose Estimation from 3D Correspondences


Title	Do not Omit Local Minimizer: a Complete Solution for Pose Estimation from 3D Correspondences
Authors	Lipu Zhou, Shengze Wang, Jiamin Ye, Michael Kaess
Abstract	Estimating pose from given 3D correspondences, including point-to-point, point-to-line and point-to-plane correspondences, is a fundamental task in computer vision with many applications. We present a complete solution for this task, including a solution for the minimal problem and the least-squares problem of this task. Previous works mainly focused on finding the global minimizer to address the least-squares problem. However, existing works that show the ability to achieve global minimizer are still unsuitable for real-time applications. Furthermore, as one of contributions of this paper, we prove that there exist ambiguous configurations for any number of lines and planes. These configurations have several solutions in theory, which makes the correct solution may come from a local minimizer. Our algorithm is efficient and able to reveal local minimizers. We employ the Cayley-Gibbs-Rodriguez (CGR) parameterization of the rotation to derive a general rational cost for the three cases of 3D correspondences. The main contribution of this paper is to solve the resulting equation system of the minimal problem and the first-order optimality conditions of the least-squares problem, both of which are of complicated rational forms. The central idea of our algorithm is to introduce intermediate unknowns to simplify the problem. Extensive experimental results show that our algorithm significantly outperforms previous algorithms when the number of correspondences is small. Besides, when the global minimizer is the solution, our algorithm achieves the same accuracy as previous algorithms that have guaranteed global optimality, but our algorithm is applicable to real-time applications.
Tasks	Pose Estimation
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01759v2
PDF	http://arxiv.org/pdf/1904.01759v2.pdf
PWC	https://paperswithcode.com/paper/do-not-omit-local-minimizer-a-complete
Repo
Framework

Are Out-of-Distribution Detection Methods Effective on Large-Scale Datasets?


Title	Are Out-of-Distribution Detection Methods Effective on Large-Scale Datasets?
Authors	Ryne Roady, Tyler L. Hayes, Ronald Kemker, Ayesha Gonzales, Christopher Kanan
Abstract	Supervised classification methods often assume the train and test data distributions are the same and that all classes in the test set are present in the training set. However, deployed classifiers often require the ability to recognize inputs from outside the training set as unknowns. This problem has been studied under multiple paradigms including out-of-distribution detection and open set recognition. For convolutional neural networks, there have been two major approaches: 1) inference methods to separate knowns from unknowns and 2) feature space regularization strategies to improve model robustness to outlier inputs. There has been little effort to explore the relationship between the two approaches and directly compare performance on anything other than small-scale datasets that have at most 100 categories. Using ImageNet-1K and Places-434, we identify novel combinations of regularization and specialized inference methods that perform best across multiple outlier detection problems of increasing difficulty level. We found that input perturbation and temperature scaling yield the best performance on large scale datasets regardless of the feature space regularization strategy. Improving the feature space by regularizing against a background class can be helpful if an appropriate background class can be found, but this is impractical for large scale image classification datasets.
Tasks	Image Classification, Open Set Learning, Outlier Detection, Out-of-Distribution Detection
Published	2019-10-30
URL	https://arxiv.org/abs/1910.14034v1
PDF	https://arxiv.org/pdf/1910.14034v1.pdf
PWC	https://paperswithcode.com/paper/are-out-of-distribution-detection-methods
Repo
Framework

Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning


Title	Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning
Authors	Riashat Islam, Raihan Seraj, Samin Yeasar Arnob, Doina Precup
Abstract	We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new policy after every policy gradient update. Despite enormous success of off-policy policy gradients on control tasks, existing general methods suffer from high variance and instability, partly because the policy improvement depends on gradient of the estimated value function. In this work, we present a new way of off-policy policy evaluation in actor-critic, based on the doubly robust estimators. We extend the doubly robust estimator from off-policy policy evaluation (OPE) to actor-critic algorithms that consist of a reward estimator performance model. We find that doubly robust estimation of the critic can significantly improve performance in continuous control tasks. Furthermore, in cases where the reward function is stochastic that can lead to high variance, doubly robust critic estimation can improve performance under corrupted, stochastic reward signals, indicating its usefulness for robust and safe reinforcement learning.
Tasks	Continuous Control
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05109v1
PDF	https://arxiv.org/pdf/1912.05109v1.pdf
PWC	https://paperswithcode.com/paper/doubly-robust-off-policy-actor-critic
Repo
Framework

Detecting Cyberattacks in Industrial Control Systems Using Online Learning Algorithms


Title	Detecting Cyberattacks in Industrial Control Systems Using Online Learning Algorithms
Authors	Guangxia Lia, Yulong Shena, Peilin Zhaob, Xiao Lu, Jia Liu, Yangyang Liu, Steven C. H. Hoi
Abstract	Industrial control systems are critical to the operation of industrial facilities, especially for critical infrastructures, such as refineries, power grids, and transportation systems. Similar to other information systems, a significant threat to industrial control systems is the attack from cyberspace—the offensive maneuvers launched by “anonymous” in the digital world that target computer-based assets with the goal of compromising a system’s functions or probing for information. Owing to the importance of industrial control systems, and the possibly devastating consequences of being attacked, significant endeavors have been attempted to secure industrial control systems from cyberattacks. Among them are intrusion detection systems that serve as the first line of defense by monitoring and reporting potentially malicious activities. Classical machine-learning-based intrusion detection methods usually generate prediction models by learning modest-sized training samples all at once. Such approach is not always applicable to industrial control systems, as industrial control systems must process continuous control commands with limited computational resources in a nonstop way. To satisfy such requirements, we propose using online learning to learn prediction models from the controlling data stream. We introduce several state-of-the-art online learning algorithms categorically, and illustrate their efficacies on two typically used testbeds—power system and gas pipeline. Further, we explore a new cost-sensitive online learning algorithm to solve the class-imbalance problem that is pervasive in industrial intrusion detection systems. Our experimental results indicate that the proposed algorithm can achieve an overall improvement in the detection rate of cyberattacks in industrial control systems.
Tasks	Continuous Control, Intrusion Detection
Published	2019-12-08
URL	https://arxiv.org/abs/1912.03589v1
PDF	https://arxiv.org/pdf/1912.03589v1.pdf
PWC	https://paperswithcode.com/paper/detecting-cyberattacks-in-industrial-control-1
Repo
Framework

Representation Theoretic Patterns in Multi-Frequency Class Averaging for Three-Dimensional Cryo-Electron Microscopy


Title	Representation Theoretic Patterns in Multi-Frequency Class Averaging for Three-Dimensional Cryo-Electron Microscopy
Authors	Tingran Gao, Yifeng Fan, Zhizhen Zhao
Abstract	We develop in this paper a novel intrinsic classification algorithm – multi-frequency class averaging (MFCA) – for clustering noisy projection images obtained from three-dimensional cryo-electron microscopy (cryo-EM) by the similarity among their viewing directions. This new algorithm leverages multiple irreducible representations of the unitary group to introduce additional redundancy into the representation of the transport data, extending and outperforming the previous class averaging algorithm of Hadani and Singer [Foundations of Computational Mathematics, 11 (5), pp. 589–616 (2011)] that uses only a single representation. The formal algebraic model and representation theoretic patterns of the proposed MFCA algorithm extend the framework of Hadani and Singer to arbitrary irreducible representations of the unitary group. We conceptually establish the consistency and stability of MFCA by inspecting the spectral properties of a generalized localized parallel transport operator on the two-dimensional unit sphere through the lens of Wigner matrices. We demonstrate the efficacy of the proposed algorithm with numerical experiments.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1906.01082v2
PDF	https://arxiv.org/pdf/1906.01082v2.pdf
PWC	https://paperswithcode.com/paper/representation-theoretic-patterns-in-multi
Repo
Framework

Understanding Deep Learning Techniques for Image Segmentation


Title	Understanding Deep Learning Techniques for Image Segmentation
Authors	Swarnendu Ghosh, Nibaran Das, Ishita Das, Ujjwal Maulik
Abstract	The machine learning community has been overwhelmed by a plethora of deep learning based approaches. Many challenging computer vision tasks such as detection, localization, recognition and segmentation of objects in unconstrained environment are being efficiently addressed by various types of deep neural networks like convolutional neural networks, recurrent networks, adversarial networks, autoencoders and so on. While there have been plenty of analytical studies regarding the object detection or recognition domain, many new deep learning techniques have surfaced with respect to image segmentation techniques. This paper approaches these various deep learning techniques of image segmentation from an analytical perspective. The main goal of this work is to provide an intuitive understanding of the major techniques that has made significant contribution to the image segmentation domain. Starting from some of the traditional image segmentation approaches, the paper progresses describing the effect deep learning had on the image segmentation domain. Thereafter, most of the major segmentation algorithms have been logically categorized with paragraphs dedicated to their unique contribution. With an ample amount of intuitive explanations, the reader is expected to have an improved ability to visualize the internal dynamics of these processes.
Tasks	Object Detection, Semantic Segmentation
Published	2019-07-13
URL	https://arxiv.org/abs/1907.06119v1
PDF	https://arxiv.org/pdf/1907.06119v1.pdf
PWC	https://paperswithcode.com/paper/understanding-deep-learning-techniques-for
Repo
Framework

On-policy Reinforcement Learning with Entropy Regularization


Title	On-policy Reinforcement Learning with Entropy Regularization
Authors	Jingbin Liu, Xinyang Gu, Dexiang Zhang, Shuai Liu
Abstract	Entropy regularization is an imported idea in reinforcement learning, with great success in recent algorithms like Soft Actor Critic and Soft Q Network. In this work we extend this idea into the on-policy realm. With the soft gradient policy theorem, we construct the maximum entropy reinforcement learning framework for on-policy RL. For policy gradient based on-policy algorithms, policy network is often represented as Gaussian distribution with the action variance restricted to be global for all the states observed from the environment. We propose an idea called action variance scale for policy network and find it can work collaboratively with the idea of entropy regularization. In this paper, we choose the state-of-the-art on-policy algorithm, Proximal Policy Optimization, as our basal algorithm and present Soft Proximal Policy Optimization (SPPO). PPO is a popular on-policy RL algorithm with great stability and parallelism. But like many on-policy algorithm, PPO can also suffer from low sample efficiency and local optimum problem. In the entropy-regularized framework, SPPO can guide the agent to succeed at the task while maintaining exploration by acting as randomly as possible. Our method outperforms prior works on a range of continuous control benchmark tasks, Furthermore, our method can be easily extended to large scale experiment and achieve stable learning at high throughput.
Tasks	Continuous Control
Published	2019-12-02
URL	https://arxiv.org/abs/1912.01557v2
PDF	https://arxiv.org/pdf/1912.01557v2.pdf
PWC	https://paperswithcode.com/paper/on-policy-reinforcement-learning-with-entropy
Repo
Framework

Prediction Model for Semitransparent Watercolor Pigment Mixtures Using Deep Learning with a Dataset of Transmittance and Reflectance


Title	Prediction Model for Semitransparent Watercolor Pigment Mixtures Using Deep Learning with a Dataset of Transmittance and Reflectance
Authors	Mei-Yun Chen, Ya-Bo Huang, Sheng-Ping Chang, Ming Ouhyoung
Abstract	Learning color mixing is difficult for novice painters. In order to support novice painters in learning color mixing, we propose a prediction model for semitransparent pigment mixtures and use its prediction results to create a Smart Palette system. Such a system is constructed by first building a watercolor dataset with two types of color mixing data, indicated by transmittance and reflectance: incrementation of the same primary pigment and a mixture of two different pigments. Next, we apply the collected data to a deep neural network to train a model for predicting the results of semitransparent pigment mixtures. Finally, we constructed a Smart Palette that provides easily-followable instructions on mixing a target color with two primary pigments in real life: when users pick a pixel, an RGB color, from an image, the system returns its mixing recipe which indicates the two primary pigments being used and their quantities.
Tasks
Published	2019-03-30
URL	http://arxiv.org/abs/1904.00275v1
PDF	http://arxiv.org/pdf/1904.00275v1.pdf
PWC	https://paperswithcode.com/paper/prediction-model-for-semitransparent
Repo
Framework

Deep Landscape Features for Improving Vector-borne Disease Prediction


Title	Deep Landscape Features for Improving Vector-borne Disease Prediction
Authors	Nabeel Abdur Rehman, Umar Saif, Rumi Chunara
Abstract	The global population at risk of mosquito-borne diseases such as dengue, yellow fever, chikungunya and Zika is expanding. Infectious disease models commonly incorporate environmental measures like temperature and precipitation. Given increasing availability of high-resolution satellite imagery, here we consider including landscape features from satellite imagery into infectious disease prediction models. To do so, we implement a Convolutional Neural Network (CNN) model trained on Imagenet data and labelled landscape features in satellite data from London. We then incorporate landscape features from satellite image data from Pakistan, labelled using the CNN, in a well-known Susceptible-Infectious-Recovered epidemic model, alongside dengue case data from 2012-2016 in Pakistan. We study improvement of the prediction model for each of the individual landscape features, and assess the feasibility of using image labels from a different place. We find that incorporating satellite-derived landscape features can improve prediction of outbreaks, which is important for proactive and strategic surveillance and control programmes.
Tasks	Disease Prediction
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01994v1
PDF	http://arxiv.org/pdf/1904.01994v1.pdf
PWC	https://paperswithcode.com/paper/deep-landscape-features-for-improving-vector
Repo
Framework

Turing Test Revisited: A Framework for an Alternative


Title	Turing Test Revisited: A Framework for an Alternative
Authors	Aladdin Ayesh
Abstract	This paper aims to question the suitability of the Turing Test, for testing machine intelligence, in the light of advances made in the last 60 years in science, medicine, and philosophy of mind. While the main concept of the test may seem sound and valid, a detailed analysis of what is required to pass the test highlights a significant flow. Once the analysis of the test is presented, a systematic approach is followed in analysing what is needed to devise a test or tests for intelligent machines. The paper presents a plausible generic framework based on categories of factors implied by subjective perception of intelligence. An evaluative discussion concludes the paper highlighting some of the unaddressed issues within this generic framework.
Tasks
Published	2019-06-26
URL	https://arxiv.org/abs/1906.11068v1
PDF	https://arxiv.org/pdf/1906.11068v1.pdf
PWC	https://paperswithcode.com/paper/turing-test-revisited-a-framework-for-an
Repo
Framework

Effective Decoding in Graph Auto-Encoder using Triadic Closure


Title	Effective Decoding in Graph Auto-Encoder using Triadic Closure
Authors	Han Shi, Haozheng Fan, James T. Kwok
Abstract	The (variational) graph auto-encoder and its variants have been popularly used for representation learning on graph-structured data. While the encoder is often a powerful graph convolutional network, the decoder reconstructs the graph structure by only considering two nodes at a time, thus ignoring possible interactions among edges. On the other hand, structured prediction, which considers the whole graph simultaneously, is computationally expensive. In this paper, we utilize the well-known triadic closure property which is exhibited in many real-world networks. We propose the triad decoder, which considers and predicts the three edges involved in a local triad together. The triad decoder can be readily used in any graph-based auto-encoder. In particular, we incorporate this to the (variational) graph auto-encoder. Experiments on link prediction, node clustering and graph generation show that the use of triads leads to more accurate prediction, clustering and better preservation of the graph characteristics.
Tasks	Graph Generation, Link Prediction, Representation Learning, Structured Prediction
Published	2019-11-26
URL	https://arxiv.org/abs/1911.11322v1
PDF	https://arxiv.org/pdf/1911.11322v1.pdf
PWC	https://paperswithcode.com/paper/effective-decoding-in-graph-auto-encoder
Repo
Framework

PC-Fairness: A Unified Framework for Measuring Causality-based Fairness


Title	PC-Fairness: A Unified Framework for Measuring Causality-based Fairness
Authors	Yongkai Wu, Lu Zhang, Xintao Wu, Hanghang Tong
Abstract	A recent trend of fair machine learning is to define fairness as causality-based notions which concern the causal connection between protected attributes and decisions. However, one common challenge of all causality-based fairness notions is identifiability, i.e., whether they can be uniquely measured from observational data, which is a critical barrier to applying these notions to real-world situations. In this paper, we develop a framework for measuring different causality-based fairness. We propose a unified definition that covers most of previous causality-based fairness notions, namely the path-specific counterfactual fairness (PC fairness). Based on that, we propose a general method in the form of a constrained optimization problem for bounding the path-specific counterfactual fairness under all unidentifiable situations. Experiments on synthetic and real-world datasets show the correctness and effectiveness of our method.
Tasks
Published	2019-10-20
URL	https://arxiv.org/abs/1910.12586v1
PDF	https://arxiv.org/pdf/1910.12586v1.pdf
PWC	https://paperswithcode.com/paper/pc-fairness-a-unified-framework-for-measuring
Repo
Framework

Closing the Reality Gap with Unsupervised Sim-to-Real Image Translation for Semantic Segmentation in Robot Soccer


Title	Closing the Reality Gap with Unsupervised Sim-to-Real Image Translation for Semantic Segmentation in Robot Soccer
Authors	Jan Blumenkamp, Andreas Baude, Tim Laue
Abstract	Deep learning approaches have become the standard solution to many problems in computer vision and robotics, but obtaining proper and sufficient training data is often a problem, as human labor is often error prone, time consuming and expensive. Solutions based on simulation have become more popular in recent years, but the gap between simulation and reality is still a major issue. In this paper, we introduce a novel model for augmenting synthetic image data through unsupervised image-to-image translation by applying the style of real world images to simulated images with open source frameworks. This model intends to generate the training data as a separate step and not as part of the training. The generated dataset is combined with conventional augmentation methods and is then applied to a neural network capable of running in real-time on autonomous soccer robots. Our evaluation shows a significant improvement compared to networks trained on simulated images without this kind of augmentation.
Tasks	Image-to-Image Translation, Semantic Segmentation, Unsupervised Image-To-Image Translation
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01529v1
PDF	https://arxiv.org/pdf/1911.01529v1.pdf
PWC	https://paperswithcode.com/paper/closing-the-reality-gap-with-unsupervised-sim
Repo
Framework

KL property of exponent $1/2$ of $\ell_{2,0}$-norm and DC regularized factorizations for low-rank matrix recovery


Title	KL property of exponent $1/2$ of $\ell_{2,0}$-norm and DC regularized factorizations for low-rank matrix recovery
Authors	Shujun Bi, Ting Tao, Shaohua Pan
Abstract	This paper is concerned with the factorization form of the rank regularized loss minimization problem. To cater for the scenario in which only a coarse estimation is available for the rank of the true matrix, an $\ell_{2,0}$-norm regularized term is added to the factored loss function to reduce the rank adaptively; and account for the ambiguities in the factorization, a balanced term is then introduced. For the least squares loss, under a restricted condition number assumption on the sampling operator, we establish the KL property of exponent $1/2$ of the nonsmooth factored composite function and its equivalent DC reformulations in the set of their global minimizers. We also confirm the theoretical findings by applying a proximal linearized alternating minimization method to the regularized factorizations.
Tasks
Published	2019-08-24
URL	https://arxiv.org/abs/1908.09078v1
PDF	https://arxiv.org/pdf/1908.09078v1.pdf
PWC	https://paperswithcode.com/paper/kl-property-of-exponent-12-of-ell_20-norm-and
Repo
Framework