January 30, 2020

3176 words 15 mins read

Paper Group ANR 353

What Do You Mean I’m Funny? Personalizing the Joke Skill of a Voice-Controlled Virtual Assistant. Deep reinforcement learning for complex evaluation of one-loop diagrams in quantum field theory. Consistency Regularization for Generative Adversarial Networks. AMASS: Archive of Motion Capture as Surface Shapes. Sensory Optimization: Neural Networks a …

What Do You Mean I’m Funny? Personalizing the Joke Skill of a Voice-Controlled Virtual Assistant


Title	What Do You Mean I’m Funny? Personalizing the Joke Skill of a Voice-Controlled Virtual Assistant
Authors	Alejandro Mottini, Amber Roy Chowdhury
Abstract	A considerable part of the success experienced by Voice-controlled virtual assistants (VVA) is due to the emotional and personalized experience they deliver, with humor being a key component in providing an engaging interaction. In this paper we describe methods used to improve the joke skill of a VVA through personalization. The first method, based on traditional NLP techniques, is robust and scalable. The others combine self-attentional network and multi-task learning to obtain better results, at the cost of added complexity. A significant challenge facing these systems is the lack of explicit user feedback needed to provide labels for the models. Instead, we explore the use of two implicit feedback-based labelling strategies. All models were evaluated on real production data. Online results show that models trained on any of the considered labels outperform a heuristic method, presenting a positive real-world impact on user satisfaction. Offline results suggest that the deep-learning approaches can improve the joke experience with respect to the other considered methods.
Tasks	Multi-Task Learning
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03234v1
PDF	https://arxiv.org/pdf/1912.03234v1.pdf
PWC	https://paperswithcode.com/paper/what-do-you-mean-im-funny-personalizing-the
Repo
Framework

Deep reinforcement learning for complex evaluation of one-loop diagrams in quantum field theory


Title	Deep reinforcement learning for complex evaluation of one-loop diagrams in quantum field theory
Authors	Andreas Windisch, Thomas Gallien, Christopher Schwarzlmueller
Abstract	In this paper we present a novel technique based on deep reinforcement learning that allows for numerical analytic continuation of integrals that are often encountered in one-loop diagrams in quantum field theory. In order to extract certain quantities of two-point functions, such as spectral densities, mass poles or multi-particle thresholds, it is necessary to perform an analytic continuation of the correlator in question. At one-loop level in Euclidean space, this results in the necessity to deform the integration contour of the loop integral in the complex plane of the square of the loop momentum, in order to avoid non-analyticities in the integration plane. Using a toy model for which an exact solution is known, we train a reinforcement learning agent to perform the required contour deformations. Our study shows great promise for an agent to be deployed in iterative numerical approaches used to compute non-perturbative 2-point functions, such as the quark propagator Dyson-Schwinger equation, or more generally, Fredholm equations of the second kind, in the complex domain.
Tasks
Published	2019-12-27
URL	https://arxiv.org/abs/1912.12322v1
PDF	https://arxiv.org/pdf/1912.12322v1.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-for-complex
Repo
Framework

Consistency Regularization for Generative Adversarial Networks


Title	Consistency Regularization for Generative Adversarial Networks
Authors	Han Zhang, Zizhao Zhang, Augustus Odena, Honglak Lee
Abstract	Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have been proposed, but they introduce non-trivial computational overheads and interact poorly with existing techniques like spectral normalization. In this work, we propose a simple, effective training stabilizer based on the notion of consistency regularization—a popular technique in the semi-supervised learning literature. In particular, we augment data passing into the GAN discriminator and penalize the sensitivity of the discriminator to these augmentations. We conduct a series of experiments to demonstrate that consistency regularization works effectively with spectral normalization and various GAN architectures, loss functions and optimizer settings. Our method achieves the best FID scores for unconditional image generation compared to other regularization methods on CIFAR-10 and CelebA. Moreover, Our consistency regularized GAN (CR-GAN) improves state-of-the-art FID scores for conditional generation from 14.73 to 11.48 on CIFAR-10 and from 8.73 to 6.66 on ImageNet-2012.
Tasks	Conditional Image Generation, Image Generation
Published	2019-10-26
URL	https://arxiv.org/abs/1910.12027v2
PDF	https://arxiv.org/pdf/1910.12027v2.pdf
PWC	https://paperswithcode.com/paper/consistency-regularization-for-generative-1
Repo
Framework

AMASS: Archive of Motion Capture as Surface Shapes


Title	AMASS: Archive of Motion Capture as Surface Shapes
Authors	Naureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll, Michael J. Black
Abstract	Large datasets are the cornerstone of recent advances in computer vision using deep learning. In contrast, existing human motion capture (mocap) datasets are small and the motions limited, hampering progress on learning models of human motion. While there are many different datasets available, they each use a different parameterization of the body, making it difficult to integrate them into a single meta dataset. To address this, we introduce AMASS, a large and varied database of human motion that unifies 15 different optical marker-based mocap datasets by representing them within a common framework and parameterization. We achieve this using a new method, MoSh++, that converts mocap data into realistic 3D human meshes represented by a rigged body model; here we use SMPL [doi:10.1145/2816795.2818013], which is widely used and provides a standard skeletal representation as well as a fully rigged surface mesh. The method works for arbitrary marker sets, while recovering soft-tissue dynamics and realistic hand motion. We evaluate MoSh++ and tune its hyperparameters using a new dataset of 4D body scans that are jointly recorded with marker-based mocap. The consistent representation of AMASS makes it readily useful for animation, visualization, and generating training data for deep learning. Our dataset is significantly richer than previous human motion collections, having more than 40 hours of motion data, spanning over 300 subjects, more than 11,000 motions, and will be publicly available to the research community.
Tasks	Motion Capture
Published	2019-04-05
URL	http://arxiv.org/abs/1904.03278v1
PDF	http://arxiv.org/pdf/1904.03278v1.pdf
PWC	https://paperswithcode.com/paper/amass-archive-of-motion-capture-as-surface
Repo
Framework

Sensory Optimization: Neural Networks as a Model for Understanding and Creating Art


Title	Sensory Optimization: Neural Networks as a Model for Understanding and Creating Art
Authors	Owain Evans
Abstract	This article is about the cognitive science of visual art. Artists create physical artifacts (such as sculptures or paintings) which depict people, objects, and events. These depictions are usually stylized rather than photo-realistic. How is it that humans are able to understand and create stylized representations? Does this ability depend on general cognitive capacities or an evolutionary adaptation for art? What role is played by learning and culture? Machine Learning can shed light on these questions. It’s possible to train convolutional neural networks (CNNs) to recognize objects without training them on any visual art. If such CNNs can generalize to visual art (by creating and understanding stylized representations), then CNNs provide a model for how humans could understand art without innate adaptations or cultural learning. I argue that Deep Dream and Style Transfer show that CNNs can create a basic form of visual art, and that humans could create art by similar processes. This suggests that artists make art by optimizing for effects on the human object-recognition system. Physical artifacts are optimized to evoke real-world objects for this system (e.g. to evoke people or landscapes) and to serve as superstimuli for this system.
Tasks	Object Recognition, Style Transfer
Published	2019-11-16
URL	https://arxiv.org/abs/1911.07068v1
PDF	https://arxiv.org/pdf/1911.07068v1.pdf
PWC	https://paperswithcode.com/paper/sensory-optimization-neural-networks-as-a
Repo
Framework

Learning Hawkes Processes from a Handful of Events


Title	Learning Hawkes Processes from a Handful of Events
Authors	Farnood Salehi, William Trouleau, Matthias Grossglauser, Patrick Thiran
Abstract	Learning the causal-interaction network of multivariate Hawkes processes is a useful task in many applications. Maximum-likelihood estimation is the most common approach to solve the problem in the presence of long observation sequences. However, when only short sequences are available, the lack of data amplifies the risk of overfitting and regularization becomes critical. Due to the challenges of hyper-parameter tuning, state-of-the-art methods only parameterize regularizers by a single shared hyper-parameter, hence limiting the power of representation of the model. To solve both issues, we develop in this work an efficient algorithm based on variational expectation-maximization. Our approach is able to optimize over an extended set of hyper-parameters. It is also able to take into account the uncertainty in the model parameters by learning a posterior distribution over them. Experimental results on both synthetic and real datasets show that our approach significantly outperforms state-of-the-art methods under short observation sequences.
Tasks
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00292v1
PDF	https://arxiv.org/pdf/1911.00292v1.pdf
PWC	https://paperswithcode.com/paper/learning-hawkes-processes-from-a-handful-of
Repo
Framework

Convergence Analysis of Block Coordinate Algorithms with Determinantal Sampling


Title	Convergence Analysis of Block Coordinate Algorithms with Determinantal Sampling
Authors	Mojmír Mutný, Michał Dereziński, Andreas Krause
Abstract	We analyze the convergence rate of the randomized Newton-like method introduced by Qu et. al. (2016) for smooth and convex objectives, which uses random coordinate blocks of a Hessian-over-approximation matrix $\bM$ instead of the true Hessian. The convergence analysis of the algorithm is challenging because of its complex dependence on the structure of $\bM$. However, we show that when the coordinate blocks are sampled with probability proportional to their determinant, the convergence rate depends solely on the eigenvalue distribution of matrix $\bM$, and has an analytically tractable form. To do so, we derive a fundamental new expectation formula for determinantal point processes. We show that determinantal sampling allows us to reason about the optimal subset size of blocks in terms of the spectrum of $\bM$. Additionally, we provide a numerical evaluation of our analysis, demonstrating cases where determinantal sampling is superior or on par with uniform sampling.
Tasks	Point Processes
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11561v3
PDF	https://arxiv.org/pdf/1910.11561v3.pdf
PWC	https://paperswithcode.com/paper/convergence-analysis-of-the-randomized-newton
Repo
Framework

Energy-aware Scheduling of Jobs in Heterogeneous Cluster Systems Using Deep Reinforcement Learning


Title	Energy-aware Scheduling of Jobs in Heterogeneous Cluster Systems Using Deep Reinforcement Learning
Authors	Amirhossein Esmaili, Massoud Pedram
Abstract	Energy consumption is one of the most critical concerns in designing computing devices, ranging from portable embedded systems to computer cluster systems. Furthermore, in the past decade, cluster systems have increasingly risen as popular platforms to run computing-intensive real-time applications in which the performance is of great importance. However, due to different characteristics of real-time workloads, developing general job scheduling solutions that efficiently address both energy consumption and performance in real-time cluster systems is a challenging problem. In this paper, inspired by recent advances in applying deep reinforcement learning for resource management problems, we present the Deep-EAS scheduler that learns efficient energy-aware scheduling strategies for workloads with different characteristics without initially knowing anything about the scheduling task at hand. Results show that Deep-EAS converges quickly, and performs better compared to standard manually-tuned heuristics, especially in heavy load conditions.
Tasks
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05160v1
PDF	https://arxiv.org/pdf/1912.05160v1.pdf
PWC	https://paperswithcode.com/paper/energy-aware-scheduling-of-jobs-in
Repo
Framework

FishNet: A Camera Localizer using Deep Recurrent Networks


Title	FishNet: A Camera Localizer using Deep Recurrent Networks
Authors	Hsin-I Chen, Sebastian Agethen, Chiamin Wu, Winston Hsu, Bing-Yu Chen
Abstract	This paper proposes a robust localization system that employs deep learning for better scene representation, and enhances the accuracy of 6-DOF camera pose estimation. Inspired by the fact that global scene structure can be revealed by wide field-of-view, we leverage the large overlap of a fisheye camera between adjacent frames, and the powerful high-level feature representations of deep learning. Our main contribution is the novel network architecture that extracts both temporal and spatial information using a Recurrent Neural Network. Specifically, we propose a novel pose regularization term combined with LSTM. This leads to smoother pose estimation, especially for large outdoor scenery. Promising experimental results on three benchmark datasets manifest the effectiveness of the proposed approach.
Tasks	Pose Estimation
Published	2019-04-22
URL	http://arxiv.org/abs/1904.09722v1
PDF	http://arxiv.org/pdf/1904.09722v1.pdf
PWC	https://paperswithcode.com/paper/fishnet-a-camera-localizer-using-deep
Repo
Framework

L*-Based Learning of Markov Decision Processes (Extended Version)


Title	L*-Based Learning of Markov Decision Processes (Extended Version)
Authors	Martin Tappler, Bernhard K. Aichernig, Giovanni Bacci, Maria Eichlseder, Kim G. Larsen
Abstract	Automata learning techniques automatically generate system models from test observations. These techniques usually fall into two categories: passive and active. Passive learning uses a predetermined data set, e.g., system logs. In contrast, active learning actively queries the system under learning, which is considered more efficient. An influential active learning technique is Angluin’s L* algorithm for regular languages which inspired several generalisations from DFAs to other automata-based modelling formalisms. In this work, we study L*-based learning of deterministic Markov decision processes, first assuming an ideal setting with perfect information. Then, we relax this assumption and present a novel learning algorithm that collects information by sampling system traces via testing. Experiments with the implementation of our sampling-based algorithm suggest that it achieves better accuracy than state-of-the-art passive learning techniques with the same amount of test data. Unlike existing learning algorithms with predefined states, our algorithm learns the complete model structure including the states.
Tasks	Active Learning
Published	2019-06-28
URL	https://arxiv.org/abs/1906.12239v1
PDF	https://arxiv.org/pdf/1906.12239v1.pdf
PWC	https://paperswithcode.com/paper/l-based-learning-of-markov-decision-processes
Repo
Framework

Guess What’s on my Screen? Clustering Smartphone Screenshots with Active Learning


Title	Guess What’s on my Screen? Clustering Smartphone Screenshots with Active Learning
Authors	Agnese Chiatti, Dolzodmaa Davaasuren, Nilam Ram, Prasenjit Mitra, Byron Reeves, Thomas Robinson
Abstract	A significant proportion of individuals’ daily activities is experienced through digital devices. Smartphones in particular have become one of the preferred interfaces for content consumption and social interaction. Identifying the content embedded in frequently-captured smartphone screenshots is thus a crucial prerequisite to studies of media behavior and health intervention planning that analyze activity interplay and content switching over time. Screenshot images can depict heterogeneous contents and applications, making the a priori definition of adequate taxonomies a cumbersome task, even for humans. Privacy protection of the sensitive data captured on screens means the costs associated with manual annotation are large, as the effort cannot be crowd-sourced. Thus, there is need to examine utility of unsupervised and semi-supervised methods for digital screenshot classification. This work introduces the implications of applying clustering on large screenshot sets when only a limited amount of labels is available. In this paper we develop a framework for combining K-Means clustering with Active Learning for efficient leveraging of labeled and unlabeled samples, with the goal of discovering latent classes and describing a large collection of screenshot data. We tested whether SVM-embedded or XGBoost-embedded solutions for class probability propagation provide for more well-formed cluster configurations. Visual and textual vector representations of the screenshot images are derived and combined to assess the relative contribution of multi-modal features to the overall performance.
Tasks	Active Learning
Published	2019-01-09
URL	http://arxiv.org/abs/1901.02701v2
PDF	http://arxiv.org/pdf/1901.02701v2.pdf
PWC	https://paperswithcode.com/paper/guess-whats-on-my-screen-clustering
Repo
Framework

Introducing Super Pseudo Panels: Application to Transport Preference Dynamics


Title	Introducing Super Pseudo Panels: Application to Transport Preference Dynamics
Authors	Stanislav S. Borysov, Jeppe Rich
Abstract	We propose a new approach for constructing synthetic pseudo-panel data from cross-sectional data. The pseudo panel and the preferences it intends to describe is constructed at the individual level and is not affected by aggregation bias across cohorts. This is accomplished by creating a high-dimensional probabilistic model representation of the entire data set, which allows sampling from the probabilistic model in such a way that all of the intrinsic correlation properties of the original data are preserved. The key to this is the use of deep learning algorithms based on the Conditional Variational Autoencoder (CVAE) framework. From a modelling perspective, the concept of a model-based resampling creates a number of opportunities in that data can be organized and constructed to serve very specific needs of which the forming of heterogeneous pseudo panels represents one. The advantage, in that respect, is the ability to trade a serious aggregation bias (when aggregating into cohorts) for an unsystematic noise disturbance. Moreover, the approach makes it possible to explore high-dimensional sparse preference distributions and their linkage to individual specific characteristics, which is not possible if applying traditional pseudo-panel methods. We use the presented approach to reveal the dynamics of transport preferences for a fixed pseudo panel of individuals based on a large Danish cross-sectional data set covering the period from 2006 to 2016. The model is also utilized to classify individuals into ‘slow’ and ‘fast’ movers with respect to the speed at which their preferences change over time. It is found that the prototypical fast mover is a young woman who lives as a single in a large city whereas the typical slow mover is a middle-aged man with high income from a nuclear family who lives in a detached house outside a city.
Tasks
Published	2019-03-01
URL	http://arxiv.org/abs/1903.00516v1
PDF	http://arxiv.org/pdf/1903.00516v1.pdf
PWC	https://paperswithcode.com/paper/introducing-super-pseudo-panels-application
Repo
Framework

LeTS-Drive: Driving in a Crowd by Learning from Tree Search


Title	LeTS-Drive: Driving in a Crowd by Learning from Tree Search
Authors	Panpan Cai, Yuanfu Luo, Aseem Saxena, David Hsu, Wee Sun Lee
Abstract	Autonomous driving in a crowded environment, e.g., a busy traffic intersection, is an unsolved challenge for robotics. The robot vehicle must contend with a dynamic and partially observable environment, noisy sensors, and many agents. A principled approach is to formalize it as a Partially Observable Markov Decision Process (POMDP) and solve it through online belief-tree search. To handle a large crowd and achieve real-time performance in this very challenging setting, we propose LeTS-Drive, which integrates online POMDP planning and deep learning. It consists of two phases. In the offline phase, we learn a policy and the corresponding value function by imitating the belief tree search. In the online phase, the learned policy and value function guide the belief tree search. LeTS-Drive leverages the robustness of planning and the runtime efficiency of learning to enhance the performance of both. Experimental results in simulation show that LeTS-Drive outperforms either planning or imitation learning alone and develops sophisticated driving skills.
Tasks	Autonomous Driving, Imitation Learning
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12197v1
PDF	https://arxiv.org/pdf/1905.12197v1.pdf
PWC	https://paperswithcode.com/paper/lets-drive-driving-in-a-crowd-by-learning
Repo
Framework

A reconstruction of the multipreference closure


Title	A reconstruction of the multipreference closure
Authors	Laura Giordano, Valentina Gliozzi
Abstract	The paper describes a preferential approach for dealing with exceptions in KLM preferential logics, based on the rational closure. It is well known that the rational closure does not allow an independent handling of the inheritance of different defeasible properties of concepts. Several solutions have been proposed to face this problem and the lexicographic closure is the most notable one. In this work, we consider an alternative closure construction, called the Multi Preference closure (MP-closure), that has been first considered for reasoning with exceptions in DLs. Here, we reconstruct the notion of MP-closure in the propositional case and we show that it is a natural variant of Lehmann’s lexicographic closure. Abandoning Maximal Entropy (an alternative route already considered but not explored by Lehmann) leads to a construction which exploits a different lexicographic ordering w.r.t. the lexicographic closure, and determines a preferential consequence relation rather than a rational consequence relation. We show that, building on the MP-closure semantics, rationality can be recovered, at least from the semantic point of view, resulting in a rational consequence relation which is stronger than the rational closure, but incomparable with the lexicographic closure. We also show that the MP-closure is stronger than the Relevant Closure.
Tasks
Published	2019-05-05
URL	https://arxiv.org/abs/1905.03855v1
PDF	https://arxiv.org/pdf/1905.03855v1.pdf
PWC	https://paperswithcode.com/paper/190503855
Repo
Framework

AAAI FSS-19: Artificial Intelligence in Government and Public Sector Proceedings


Title	AAAI FSS-19: Artificial Intelligence in Government and Public Sector Proceedings
Authors	Frank Stein, Alun Preece
Abstract	Proceedings of the AAAI Fall Symposium on Artificial Intelligence in Government and Public Sector, Arlington, Virginia, USA, November 7-8, 2019
Tasks
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01156v2
PDF	https://arxiv.org/pdf/1911.01156v2.pdf
PWC	https://paperswithcode.com/paper/aaai-fss-19-artificial-intelligence-in
Repo
Framework