July 29, 2019

3197 words 16 mins read

Paper Group ANR 44

Learning multiple visual domains with residual adapters. Inverse Moment Methods for Sufficient Forecasting using High-Dimensional Predictors. Containment for Rule-Based Ontology-Mediated Queries. Learning Generative Models with Sinkhorn Divergences. Security Evaluation of Pattern Classifiers under Attack. Deceased Organ Matching in Australia. Activ …

Learning multiple visual domains with residual adapters


Title	Learning multiple visual domains with residual adapters
Authors	Sylvestre-Alvise Rebuffi, Hakan Bilen, Andrea Vedaldi
Abstract	There is a growing interest in learning data representations that work well for many different types of problems and data. In this paper, we look in particular at the task of learning a single visual representation that can be successfully utilized in the analysis of very different types of images, from dog breeds to stop signs and digits. Inspired by recent work on learning networks that predict the parameters of another, we develop a tunable deep network architecture that, by means of adapter residual modules, can be steered on the fly to diverse visual domains. Our method achieves a high degree of parameter sharing while maintaining or even improving the accuracy of domain-specific representations. We also introduce the Visual Decathlon Challenge, a benchmark that evaluates the ability of representations to capture simultaneously ten very different visual domains and measures their ability to recognize well uniformly.
Tasks
Published	2017-05-22
URL	http://arxiv.org/abs/1705.08045v5
PDF	http://arxiv.org/pdf/1705.08045v5.pdf
PWC	https://paperswithcode.com/paper/learning-multiple-visual-domains-with
Repo
Framework

Inverse Moment Methods for Sufficient Forecasting using High-Dimensional Predictors


Title	Inverse Moment Methods for Sufficient Forecasting using High-Dimensional Predictors
Authors	Wei Luo, Lingzhou Xue, Jiawei Yao
Abstract	We consider forecasting a single time series using high-dimensional predictors in the presence of a possible nonlinear forecast function. The sufficient forecasting (Fan et al., 2016) used sliced inverse regression to estimate lower-dimensional sufficient indices for nonparametric forecasting using factor models. However, Fan et al. (2016) is fundamentally limited to the inverse first-moment method, by assuming the restricted fixed number of factors, linearity condition for factors, and monotone effect of factors on the response. In this work, we study the inverse second-moment method using directional regression and the inverse third-moment method to extend the methodology and applicability of the sufficient forecasting. As the number of factors diverges with the dimension of predictors, the proposed method relaxes the distributional assumption of the predictor and enhances the capability of capturing the non-monotone effect of factors on the response. We not only provide a high-dimensional analysis of inverse moment methods such as exhaustiveness and rate of convergence, but also prove their model selection consistency. The power of our proposed methods is demonstrated in both simulation studies and an empirical study of forecasting monthly macroeconomic data from Q1 1959 to Q1 2016. During our theoretical development, we prove an invariance result for inverse moment methods, which make a separate contribution to the sufficient dimension reduction.
Tasks	Dimensionality Reduction, Model Selection, Time Series
Published	2017-05-01
URL	http://arxiv.org/abs/1705.00395v1
PDF	http://arxiv.org/pdf/1705.00395v1.pdf
PWC	https://paperswithcode.com/paper/inverse-moment-methods-for-sufficient
Repo
Framework

Containment for Rule-Based Ontology-Mediated Queries


Title	Containment for Rule-Based Ontology-Mediated Queries
Authors	Pablo Barcelo, Gerald Berger, Andreas Pieris
Abstract	Many efforts have been dedicated to identifying restrictions on ontologies expressed as tuple-generating dependencies (tgds), a.k.a. existential rules, that lead to the decidability for the problem of answering ontology-mediated queries (OMQs). This has given rise to three families of formalisms: guarded, non-recursive, and sticky sets of tgds. In this work, we study the containment problem for OMQs expressed in such formalisms, which is a key ingredient for solving static analysis tasks associated with them. Our main contribution is the development of specially tailored techniques for OMQ containment under the classes of tgds stated above. This enables us to obtain sharp complexity bounds for the problems at hand, which in turn allow us to delimitate its practical applicability. We also apply our techniques to pinpoint the complexity of problems associated with two emerging applications of OMQ containment: distribution over components and UCQ rewritability of OMQs.
Tasks
Published	2017-03-23
URL	http://arxiv.org/abs/1703.07994v3
PDF	http://arxiv.org/pdf/1703.07994v3.pdf
PWC	https://paperswithcode.com/paper/containment-for-rule-based-ontology-mediated
Repo
Framework

Learning Generative Models with Sinkhorn Divergences


Title	Learning Generative Models with Sinkhorn Divergences
Authors	Aude Genevay, Gabriel Peyré, Marco Cuturi
Abstract	The ability to compare two degenerate probability distributions (i.e. two probability distributions supported on two distinct low-dimensional manifolds living in a much higher-dimensional space) is a crucial problem arising in the estimation of generative models for high-dimensional observations such as those arising in computer vision or natural language. It is known that optimal transport metrics can represent a cure for this problem, since they were specifically designed as an alternative to information divergences to handle such problematic scenarios. Unfortunately, training generative machines using OT raises formidable computational and statistical challenges, because of (i) the computational burden of evaluating OT losses, (ii) the instability and lack of smoothness of these losses, (iii) the difficulty to estimate robustly these losses and their gradients in high dimension. This paper presents the first tractable computational method to train large scale generative models using an optimal transport loss, and tackles these three issues by relying on two key ideas: (a) entropic smoothing, which turns the original OT loss into one that can be computed using Sinkhorn fixed point iterations; (b) algorithmic (automatic) differentiation of these iterations. These two approximations result in a robust and differentiable approximation of the OT loss with streamlined GPU execution. Entropic smoothing generates a family of losses interpolating between Wasserstein (OT) and Maximum Mean Discrepancy (MMD), thus allowing to find a sweet spot leveraging the geometry of OT and the favorable high-dimensional sample complexity of MMD which comes with unbiased gradient estimates. The resulting computational architecture complements nicely standard deep network generative models by a stack of extra layers implementing the loss function.
Tasks
Published	2017-06-01
URL	http://arxiv.org/abs/1706.00292v3
PDF	http://arxiv.org/pdf/1706.00292v3.pdf
PWC	https://paperswithcode.com/paper/learning-generative-models-with-sinkhorn
Repo
Framework

Security Evaluation of Pattern Classifiers under Attack


Title	Security Evaluation of Pattern Classifiers under Attack
Authors	Battista Biggio, Giorgio Fumera, Fabio Roli
Abstract	Pattern classification systems are commonly used in adversarial applications, like biometric authentication, network intrusion detection, and spam filtering, in which data can be purposely manipulated by humans to undermine their operation. As this adversarial scenario is not taken into account by classical design methods, pattern classification systems may exhibit vulnerabilities, whose exploitation may severely affect their performance, and consequently limit their practical utility. Extending pattern classification theory and design methods to adversarial settings is thus a novel and very relevant research direction, which has not yet been pursued in a systematic way. In this paper, we address one of the main open issues: evaluating at design phase the security of pattern classifiers, namely, the performance degradation under potential attacks they may incur during operation. We propose a framework for empirical evaluation of classifier security that formalizes and generalizes the main ideas proposed in the literature, and give examples of its use in three real applications. Reported results show that security evaluation can provide a more complete understanding of the classifier’s behavior in adversarial environments, and lead to better design choices.
Tasks	Intrusion Detection, Network Intrusion Detection
Published	2017-09-02
URL	http://arxiv.org/abs/1709.00609v1
PDF	http://arxiv.org/pdf/1709.00609v1.pdf
PWC	https://paperswithcode.com/paper/security-evaluation-of-pattern-classifiers
Repo
Framework

Deceased Organ Matching in Australia


Title	Deceased Organ Matching in Australia
Authors	Toby Walsh
Abstract	Despite efforts to increase the supply of organs from living donors, most kidney transplants performed in Australia still come from deceased donors. The age of these donated organs has increased substantially in recent decades as the rate of fatal accidents on roads has fallen. The Organ and Tissue Authority in Australia is therefore looking to design a new mechanism that better matches the age of the organ to the age of the patient. I discuss the design, axiomatics and performance of several candidate mechanisms that respect the special online nature of this fair division problem.
Tasks
Published	2017-10-18
URL	http://arxiv.org/abs/1710.06636v1
PDF	http://arxiv.org/pdf/1710.06636v1.pdf
PWC	https://paperswithcode.com/paper/deceased-organ-matching-in-australia
Repo
Framework

Active learning machine learns to create new quantum experiments


Title	Active learning machine learns to create new quantum experiments
Authors	Alexey A. Melnikov, Hendrik Poulsen Nautrup, Mario Krenn, Vedran Dunjko, Markus Tiersch, Anton Zeilinger, Hans J. Briegel
Abstract	How useful can machine learning be in a quantum laboratory? Here we raise the question of the potential of intelligent machines in the context of scientific research. A major motivation for the present work is the unknown reachability of various entanglement classes in quantum experiments. We investigate this question by using the projective simulation model, a physics-oriented approach to artificial intelligence. In our approach, the projective simulation system is challenged to design complex photonic quantum experiments that produce high-dimensional entangled multiphoton states, which are of high interest in modern quantum experiments. The artificial intelligence system learns to create a variety of entangled states, and improves the efficiency of their realization. In the process, the system autonomously (re)discovers experimental techniques which are only now becoming standard in modern quantum optical experiments - a trait which was not explicitly demanded from the system but emerged through the process of learning. Such features highlight the possibility that machines could have a significantly more creative role in future research.
Tasks	Active Learning
Published	2017-06-02
URL	http://arxiv.org/abs/1706.00868v3
PDF	http://arxiv.org/pdf/1706.00868v3.pdf
PWC	https://paperswithcode.com/paper/active-learning-machine-learns-to-create-new
Repo
Framework

Relational Marginal Problems: Theory and Estimation


Title	Relational Marginal Problems: Theory and Estimation
Authors	Ondrej Kuzelka, Yuyi Wang, Jesse Davis, Steven Schockaert
Abstract	In the propositional setting, the marginal problem is to find a (maximum-entropy) distribution that has some given marginals. We study this problem in a relational setting and make the following contributions. First, we compare two different notions of relational marginals. Second, we show a duality between the resulting relational marginal problems and the maximum likelihood estimation of the parameters of relational models, which generalizes a well-known duality from the propositional setting. Third, by exploiting the relational marginal formulation, we present a statistically sound method to learn the parameters of relational models that will be applied in settings where the number of constants differs between the training and test data. Furthermore, based on a relational generalization of marginal polytopes, we characterize cases where the standard estimators based on feature’s number of true groundings needs to be adjusted and we quantitatively characterize the consequences of these adjustments. Fourth, we prove bounds on expected errors of the estimated parameters, which allows us to lower-bound, among other things, the effective sample size of relational training data.
Tasks
Published	2017-09-18
URL	http://arxiv.org/abs/1709.05825v4
PDF	http://arxiv.org/pdf/1709.05825v4.pdf
PWC	https://paperswithcode.com/paper/relational-marginal-problems-theory-and
Repo
Framework

Dynamic Difficulty Adjustment on MOBA Games


Title	Dynamic Difficulty Adjustment on MOBA Games
Authors	Mirna Paula Silva, Victor do Nascimento Silva, Luiz Chaimowicz
Abstract	This paper addresses the dynamic difficulty adjustment on MOBA games as a way to improve the player’s entertainment. Although MOBA is currently one of the most played genres around the world, it is known as a game that offer less autonomy, more challenges and consequently more frustration. Due to these characteristics, the use of a mechanism that performs the difficulty balance dynamically seems to be an interesting alternative to minimize and/or avoid that players experience such frustrations. In this sense, this paper presents a dynamic difficulty adjustment mechanism for MOBA games. The main idea is to create a computer controlled opponent that adapts dynamically to the player performance, trying to offer to the player a better game experience. This is done by evaluating the performance of the player using a metric based on some game features and switching the difficulty of the opponent’s artificial intelligence behavior accordingly. Quantitative and qualitative experiments were performed and the results showed that the system is capable of adapting dynamically to the opponent’s skills. In spite of that, the qualitative experiments with users showed that the player’s expertise has a greater influence on the perception of the difficulty level and dynamic adaptation.
Tasks
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02796v1
PDF	http://arxiv.org/pdf/1706.02796v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-difficulty-adjustment-on-moba-games
Repo
Framework

Embarrassingly Parallel Inference for Gaussian Processes


Title	Embarrassingly Parallel Inference for Gaussian Processes
Authors	Michael Minyi Zhang, Sinead A. Williamson
Abstract	Training Gaussian process-based models typically involves an $ O(N^3)$ computational bottleneck due to inverting the covariance matrix. Popular methods for overcoming this matrix inversion problem cannot adequately model all types of latent functions, and are often not parallelizable. However, judicious choice of model structure can ameliorate this problem. A mixture-of-experts model that uses a mixture of $K$ Gaussian processes offers modeling flexibility and opportunities for scalable inference. Our embarrassingly parallel algorithm combines low-dimensional matrix inversions with importance sampling to yield a flexible, scalable mixture-of-experts model that offers comparable performance to Gaussian process regression at a much lower computational cost.
Tasks	Gaussian Processes
Published	2017-02-27
URL	https://arxiv.org/abs/1702.08420v9
PDF	https://arxiv.org/pdf/1702.08420v9.pdf
PWC	https://paperswithcode.com/paper/embarrassingly-parallel-inference-for
Repo
Framework

Personalized Cinemagraphs using Semantic Understanding and Collaborative Learning


Title	Personalized Cinemagraphs using Semantic Understanding and Collaborative Learning
Authors	Tae-Hyun Oh, Kyungdon Joo, Neel Joshi, Baoyuan Wang, In So Kweon, Sing Bing Kang
Abstract	Cinemagraphs are a compelling way to convey dynamic aspects of a scene. In these media, dynamic and still elements are juxtaposed to create an artistic and narrative experience. Creating a high-quality, aesthetically pleasing cinemagraph requires isolating objects in a semantically meaningful way and then selecting good start times and looping periods for those objects to minimize visual artifacts (such a tearing). To achieve this, we present a new technique that uses object recognition and semantic segmentation as part of an optimization method to automatically create cinemagraphs from videos that are both visually appealing and semantically meaningful. Given a scene with multiple objects, there are many cinemagraphs one could create. Our method evaluates these multiple candidates and presents the best one, as determined by a model trained to predict human preferences in a collaborative way. We demonstrate the effectiveness of our approach with multiple results and a user study.
Tasks	Object Recognition, Semantic Segmentation
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02970v1
PDF	http://arxiv.org/pdf/1708.02970v1.pdf
PWC	https://paperswithcode.com/paper/personalized-cinemagraphs-using-semantic
Repo
Framework

On the Fusion of Compton Scatter and Attenuation Data for Limited-view X-ray Tomographic Applications


Title	On the Fusion of Compton Scatter and Attenuation Data for Limited-view X-ray Tomographic Applications
Authors	Hamideh Rezaee, Brian Tracey, Eric L. Miller
Abstract	In this paper we demonstrate the utility of fusing energy-resolved observations of Compton scattered photons with traditional attenuation data for the joint recovery of mass density and photoelectric absorption in the context of limited view tomographic imaging applications. We begin with the development of a physical and associated numerical model for the Compton scatter process. Using this model, we propose a variational approach recovering these two material properties. In addition to the typical data-fidelity terms, the optimization functional includes regularization for both the mass density and photoelectric coefficients. We consider a novel edge-preserving method in the case of mass density. To aid in the recovery of the photoelectric information, we draw on our recent method in \cite{r15} and employ a non-local regularization scheme that builds on the fact that mass density is more stably imaged. Simulation results demonstrate clear advantages associated with the use of both scattered photon data and energy resolved information in mapping the two material properties of interest. Specifically, comparing images obtained using only conventional attenuation data with those where we employ only Compton scatter photons and images formed from the combination of the two, shows that taking advantage of both types of data for reconstruction provides far more accurate results.
Tasks
Published	2017-07-05
URL	http://arxiv.org/abs/1707.01530v1
PDF	http://arxiv.org/pdf/1707.01530v1.pdf
PWC	https://paperswithcode.com/paper/on-the-fusion-of-compton-scatter-and
Repo
Framework

A New Hybrid-parameter Recurrent Neural Networks for Online Handwritten Chinese Character Recognition


Title	A New Hybrid-parameter Recurrent Neural Networks for Online Handwritten Chinese Character Recognition
Authors	Haiqing Ren, Weiqiang Wang
Abstract	The recurrent neural network (RNN) is appropriate for dealing with temporal sequences. In this paper, we present a deep RNN with new features and apply it for online handwritten Chinese character recognition. Compared with the existing RNN models, three innovations are involved in the proposed system. First, a new hidden layer function for RNN is proposed for learning temporal information better. we call it Memory Pool Unit (MPU). The proposed MPU has a simple architecture. Second, a new RNN architecture with hybrid parameter is presented, in order to increasing the expression capacity of RNN. The proposed hybrid-parameter RNN has parameter changes when calculating the iteration at temporal dimension. Third, we make a adaptation that all the outputs of each layer are stacked as the output of network. Stacked hidden layer states combine all the hidden layer states for increasing the expression capacity. Experiments are carried out on the IAHCC-UCAS2016 dataset and the CASIA-OLHWDB1.1 dataset. The experimental results show that the hybrid-parameter RNN obtain a better recognition performance with higher efficiency (fewer parameters and faster speed). And the proposed Memory Pool Unit is proved to be a simple hidden layer function and obtains a competitive recognition results.
Tasks
Published	2017-11-08
URL	http://arxiv.org/abs/1711.02809v2
PDF	http://arxiv.org/pdf/1711.02809v2.pdf
PWC	https://paperswithcode.com/paper/a-new-hybrid-parameter-recurrent-neural
Repo
Framework

Streaming Bayesian inference: theoretical limits and mini-batch approximate message-passing


Title	Streaming Bayesian inference: theoretical limits and mini-batch approximate message-passing
Authors	Andre Manoel, Florent Krzakala, Eric W. Tramel, Lenka Zdeborová
Abstract	In statistical learning for real-world large-scale data problems, one must often resort to “streaming” algorithms which operate sequentially on small batches of data. In this work, we present an analysis of the information-theoretic limits of mini-batch inference in the context of generalized linear models and low-rank matrix factorization. In a controlled Bayes-optimal setting, we characterize the optimal performance and phase transitions as a function of mini-batch size. We base part of our results on a detailed analysis of a mini-batch version of the approximate message-passing algorithm (Mini-AMP), which we introduce. Additionally, we show that this theoretical optimality carries over into real-data problems by illustrating that Mini-AMP is competitive with standard streaming algorithms for clustering.
Tasks	Bayesian Inference
Published	2017-06-02
URL	http://arxiv.org/abs/1706.00705v1
PDF	http://arxiv.org/pdf/1706.00705v1.pdf
PWC	https://paperswithcode.com/paper/streaming-bayesian-inference-theoretical
Repo
Framework

Deep Learning from Noisy Image Labels with Quality Embedding


Title	Deep Learning from Noisy Image Labels with Quality Embedding
Authors	Jiangchao Yao, Jiajie Wang, Ivor Tsang, Ya Zhang, Jun Sun, Chengqi Zhang, Rui Zhang
Abstract	There is an emerging trend to leverage noisy image datasets in many visual recognition tasks. However, the label noise among the datasets severely degenerates the \mbox{performance of deep} learning approaches. Recently, one mainstream is to introduce the latent label to handle label noise, which has shown promising improvement in the network designs. Nevertheless, the mismatch between latent labels and noisy labels still affects the predictions in such methods. To address this issue, we propose a quality embedding model, which explicitly introduces a quality variable to represent the trustworthiness of noisy labels. Our key idea is to identify the mismatch between the latent and noisy labels by embedding the quality variables into different subspaces, which effectively minimizes the noise effect. At the same time, the high-quality labels is still able to be applied for training. To instantiate the model, we further propose a Contrastive-Additive Noise network (CAN), which consists of two important layers: (1) the contrastive layer estimates the quality variable in the embedding space to reduce noise effect; and (2) the additive layer aggregates the prior predictions and noisy labels as the posterior to train the classifier. Moreover, to tackle the optimization difficulty, we deduce an SGD algorithm with the reparameterization tricks, which makes our method scalable to big data. We conduct the experimental evaluation of the proposed method over a range of noisy image datasets. Comprehensive results have demonstrated CAN outperforms the state-of-the-art deep learning approaches.
Tasks
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00583v1
PDF	http://arxiv.org/pdf/1711.00583v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-from-noisy-image-labels-with
Repo
Framework