Paper Group ANR 701
Learning Sparse Dynamical Systems from a Single Sample Trajectory. Properties of Laplacian Pyramids for Extension and Denoising. PIQA: Reasoning about Physical Commonsense in Natural Language. Generating Interactive Worlds with Text. Best Arm Identification in Generalized Linear Bandits. Can User-Centered Reinforcement Learning Allow a Robot to Att …
Learning Sparse Dynamical Systems from a Single Sample Trajectory
| Title | Learning Sparse Dynamical Systems from a Single Sample Trajectory |
| Authors | Salar Fattahi, Nikolai Matni, Somayeh Sojoudi |
| Abstract | This paper addresses the problem of identifying sparse linear time-invariant (LTI) systems from a single sample trajectory generated by the system dynamics. We introduce a Lasso-like estimator for the parameters of the system, taking into account their sparse nature. Assuming that the system is stable, or that it is equipped with an initial stabilizing controller, we provide sharp finite-time guarantees on the accurate recovery of both the sparsity structure and the parameter values of the system. In particular, we show that the proposed estimator can correctly identify the sparsity pattern of the system matrices with high probability, provided that the length of the sample trajectory exceeds a threshold. Furthermore, we show that this threshold scales polynomially in the number of nonzero elements in the system matrices, but logarithmically in the system dimensions — this improves on existing sample complexity bounds for the sparse system identification problem. We further extend these results to obtain sharp bounds on the $\ell_{\infty}$-norm of the estimation error and show how different properties of the system—such as its stability level and \textit{mutual incoherency}—affect this bound. Finally, an extensive case study on power systems is presented to illustrate the performance of the proposed estimation method. |
| Tasks | |
| Published | 2019-04-20 |
| URL | http://arxiv.org/abs/1904.09396v1 |
| http://arxiv.org/pdf/1904.09396v1.pdf | |
| PWC | https://paperswithcode.com/paper/190409396 |
| Repo | |
| Framework | |
Properties of Laplacian Pyramids for Extension and Denoising
| Title | Properties of Laplacian Pyramids for Extension and Denoising |
| Authors | William Leeb |
| Abstract | We analyze the Laplacian pyramids algorithm of Rabin and Coifman for extending and denoising a function sampled on a discrete set of points. We provide mild conditions under which the algorithm converges, and prove stability bounds on the extended function. We also consider the iterative application of truncated Laplacian pyramids kernels for denoising signals by non-local means. |
| Tasks | Denoising |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07974v1 |
| https://arxiv.org/pdf/1909.07974v1.pdf | |
| PWC | https://paperswithcode.com/paper/properties-of-laplacian-pyramids-for |
| Repo | |
| Framework | |
PIQA: Reasoning about Physical Commonsense in Natural Language
| Title | PIQA: Reasoning about Physical Commonsense in Natural Language |
| Authors | Yonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao, Yejin Choi |
| Abstract | To apply eyeshadow without a brush, should I use a cotton swab or a toothpick? Questions requiring this kind of physical commonsense pose a challenge to today’s natural language understanding systems. While recent pretrained models (such as BERT) have made progress on question answering over more abstract domains - such as news articles and encyclopedia entries, where text is plentiful - in more physical domains, text is inherently limited due to reporting bias. Can AI systems learn to reliably answer physical common-sense questions without experiencing the physical world? In this paper, we introduce the task of physical commonsense reasoning and a corresponding benchmark dataset Physical Interaction: Question Answering or PIQA. Though humans find the dataset easy (95% accuracy), large pretrained models struggle (77%). We provide analysis about the dimensions of knowledge that existing models lack, which offers significant opportunities for future research. |
| Tasks | Common Sense Reasoning, Question Answering |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11641v1 |
| https://arxiv.org/pdf/1911.11641v1.pdf | |
| PWC | https://paperswithcode.com/paper/piqa-reasoning-about-physical-commonsense-in |
| Repo | |
| Framework | |
Generating Interactive Worlds with Text
| Title | Generating Interactive Worlds with Text |
| Authors | Angela Fan, Jack Urbanek, Pratik Ringshia, Emily Dinan, Emma Qian, Siddharth Karamcheti, Shrimai Prabhumoye, Douwe Kiela, Tim Rocktaschel, Arthur Szlam, Jason Weston |
| Abstract | Procedurally generating cohesive and interesting game environments is challenging and time-consuming. In order for the relationships between the game elements to be natural, common-sense has to be encoded into arrangement of the elements. In this work, we investigate a machine learning approach for world creation using content from the multi-player text adventure game environment LIGHT. We introduce neural network based models to compositionally arrange locations, characters, and objects into a coherent whole. In addition to creating worlds based on existing elements, our models can generate new game content. Humans can also leverage our models to interactively aid in worldbuilding. We show that the game environments created with our approach are cohesive, diverse, and preferred by human evaluators compared to other machine learning based world construction algorithms. |
| Tasks | Common Sense Reasoning |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.09194v2 |
| https://arxiv.org/pdf/1911.09194v2.pdf | |
| PWC | https://paperswithcode.com/paper/generating-interactive-worlds-with-text |
| Repo | |
| Framework | |
Best Arm Identification in Generalized Linear Bandits
| Title | Best Arm Identification in Generalized Linear Bandits |
| Authors | Abbas Kazerouni, Lawrence M. Wein |
| Abstract | Motivated by drug design, we consider the best-arm identification problem in generalized linear bandits. More specifically, we assume each arm has a vector of covariates, there is an unknown vector of parameters that is common across the arms, and a generalized linear model captures the dependence of rewards on the covariate and parameter vectors. The problem is to minimize the number of arm pulls required to identify an arm that is sufficiently close to optimal with a sufficiently high probability. Building on recent progress in best-arm identification for linear bandits (Xu et al. 2018), we propose the first algorithm for best-arm identification for generalized linear bandits, provide theoretical guarantees on its accuracy and sampling efficiency, and evaluate its performance in various scenarios via simulation. |
| Tasks | |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08224v1 |
| https://arxiv.org/pdf/1905.08224v1.pdf | |
| PWC | https://paperswithcode.com/paper/best-arm-identification-in-generalized-linear |
| Repo | |
| Framework | |
Can User-Centered Reinforcement Learning Allow a Robot to Attract Passersby without Causing Discomfort?
| Title | Can User-Centered Reinforcement Learning Allow a Robot to Attract Passersby without Causing Discomfort? |
| Authors | Yasunori Ozaki, Tatsuya Ishihara, Narimune Matsumura, Tadashi Nunobiki |
| Abstract | The aim of our study was to develop a method by which a social robot can greet passersby and get their attention without causing them to suffer discomfort.A number of customer services have recently come to be provided by social robots rather than people, including, serving as receptionists, guides, and exhibitors. Robot exhibitors, for example, can explain products being promoted by the robot owners. However, a sudden greeting by a robot can startle passersby and cause discomfort to passersby.Social robots should thus adapt their mannerisms to the situation they face regarding passersby.We developed a method for meeting this requirement on the basis of the results of related work. Our proposed method, user-centered reinforcement learning, enables robots to greet passersby and get their attention without causing them to suffer discomfort (p<0.01) .The results of an experiment in the field, an office entrance, demonstrated that our method meets this requirement. |
| Tasks | |
| Published | 2019-03-14 |
| URL | https://arxiv.org/abs/1903.05881v2 |
| https://arxiv.org/pdf/1903.05881v2.pdf | |
| PWC | https://paperswithcode.com/paper/can-robot-attract-passersby-without-causing |
| Repo | |
| Framework | |
Saliency Learning: Teaching the Model Where to Pay Attention
| Title | Saliency Learning: Teaching the Model Where to Pay Attention |
| Authors | Reza Ghaeini, Xiaoli Z. Fern, Hamed Shahbazi, Prasad Tadepalli |
| Abstract | Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches to provide insights toward the model’s behaviour and predictions, which are helpful for assessing the reliability of the model’s predictions. However, such methods do not improve the model’s reliability. In this paper, we aim to teach the model to make the right prediction for the right reason by providing explanation training and ensuring the alignment of the model’s explanation with the ground truth explanation. Our experimental results on multiple tasks and datasets demonstrate the effectiveness of the proposed method, which produces more reliable predictions while delivering better results compared to traditionally trained models. |
| Tasks | |
| Published | 2019-02-22 |
| URL | http://arxiv.org/abs/1902.08649v3 |
| http://arxiv.org/pdf/1902.08649v3.pdf | |
| PWC | https://paperswithcode.com/paper/saliency-learning-teaching-the-model-where-to |
| Repo | |
| Framework | |
A Deep Neuro-Fuzzy Network for Image Classification
| Title | A Deep Neuro-Fuzzy Network for Image Classification |
| Authors | Omolbanin Yazdanbakhsh, Scott Dick |
| Abstract | The combination of neural network and fuzzy systems into neuro-fuzzy systems integrates fuzzy reasoning rules into the connectionist networks. However, the existing neuro-fuzzy systems are developed under shallow structures having lower generalization capacity. We propose the first end-to-end deep neuro-fuzzy network and investigate its application for image classification. Two new operations are developed based on definitions of Takagi-Sugeno-Kang (TSK) fuzzy model namely fuzzy inference operation and fuzzy pooling operations; stacks of these operations comprise the layers in this network. We evaluate the network on MNIST, CIFAR-10 and CIFAR-100 datasets, finding that the network has a reasonable accuracy in these benchmarks. |
| Tasks | Image Classification |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/2001.01686v1 |
| https://arxiv.org/pdf/2001.01686v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-neuro-fuzzy-network-for-image |
| Repo | |
| Framework | |
Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling
| Title | Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling |
| Authors | Wenkai Han, Chenglu Wen, Cheng Wang, Xin Li, Qing Li |
| Abstract | Fully exploring correlation among points in point clouds is essential for their feature modeling. This paper presents a novel end-to-end graph model, named Point2Node, to represent a given point cloud. Point2Node can dynamically explore correlation among all graph nodes from different levels, and adaptively aggregate the learned features. Specifically, first, to fully explore the spatial correlation among points for enhanced feature description, in a high-dimensional node graph, we dynamically integrate the node’s correlation with self, local, and non-local nodes. Second, to more effectively integrate learned features, we design a data-aware gate mechanism to self-adaptively aggregate features at the channel level. Extensive experiments on various point cloud benchmarks demonstrate that our method outperforms the state-of-the-art. |
| Tasks | |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.10775v1 |
| https://arxiv.org/pdf/1912.10775v1.pdf | |
| PWC | https://paperswithcode.com/paper/point2node-correlation-learning-of-dynamic |
| Repo | |
| Framework | |
Answer-based Adversarial Training for Generating Clarification Questions
| Title | Answer-based Adversarial Training for Generating Clarification Questions |
| Authors | Sudha Rao, Hal Daumé III |
| Abstract | We present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that modeling hypothetical answers (to clarification questions) as latent variables can guide our approach into generating more useful clarification questions. We develop a Generative Adversarial Network (GAN) where the generator is a sequence-to-sequence model and the discriminator is a utility function that models the value of updating the context with the answer to the clarification question. We evaluate on two datasets, using both automatic metrics and human judgments of usefulness, specificity and relevance, showing that our approach outperforms both a retrieval-based model and ablations that exclude the utility model and the adversarial training. |
| Tasks | |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02281v1 |
| http://arxiv.org/pdf/1904.02281v1.pdf | |
| PWC | https://paperswithcode.com/paper/answer-based-adversarial-training-for |
| Repo | |
| Framework | |
Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory
| Title | Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory |
| Authors | Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein |
| Abstract | We empirically evaluate common assumptions about neural networks that arewidely held by practitioners and theorists alike. In this work, we: (1) prove thewidespread existence of suboptimal local minima in the loss landscape of neu-ral networks, and we use our theory to find examples; (2) show that small-normparameters are not optimal for generalization; (3) demonstrate that ResNets donot conform to wide-network theories, such as the neural tangent kernel, and thatthe interaction between skip connections and batch normalization plays a role; (4)find that rank does not correlate with generalization or robustness in a practicalsetting. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00359v2 |
| https://arxiv.org/pdf/1910.00359v2.pdf | |
| PWC | https://paperswithcode.com/paper/truth-or-backpropaganda-an-empirical-1 |
| Repo | |
| Framework | |
A Electric Network Reconfiguration Strategy with Case-Based Reasoning for the Smart Grid
| Title | A Electric Network Reconfiguration Strategy with Case-Based Reasoning for the Smart Grid |
| Authors | Flavio G. Calhau, Joberto S. B. Martins |
| Abstract | The complexity, heterogeneity and scale of electrical networks have grown far beyond the limits of exclusively human-based management at the Smart Grid (SG). Likewise, researchers cogitate the use of artificial intelligence and heuristics techniques to create cognitive and autonomic management tools that aim better assist and enhance SG management processes like in the grid reconfiguration. The development of self-healing management approaches towards a cognitive and autonomic distribution power network reconfiguration is a scenario in which the scalability and on-the-fly computation are issues. This paper proposes the use of Case-Based Reasoning (CBR) coupled with the HATSGA algorithm for the fast reconfiguration of large distribution power networks. The suitability and the scalability of the CBR-based reconfiguration strategy using HATSGA algorithm are evaluated. The evaluation indicates that the adopted HATSGA algorithm computes new reconfiguration topologies with a feasible computational time for large networks. The CBR strategy looks for managerial acceptable reconfiguration solutions at the CBR database and, as such, contributes to reduce the required number of reconfiguration computation using HATSGA. This suggests CBR can be applied with a fast reconfiguration algorithm resulting in more efficient, dynamic and cognitive grid recovery strategy. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05885v1 |
| https://arxiv.org/pdf/1907.05885v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-electric-network-reconfiguration-strategy |
| Repo | |
| Framework | |
The Snippets Taxonomy in Web Search Engines
| Title | The Snippets Taxonomy in Web Search Engines |
| Authors | Artur Strzelecki, Paulina Rutecka |
| Abstract | In this paper authors analyzed 50 000 keywords results collected from localized Polish Google search engine. We proposed a taxonomy for snippets displayed in search results as regular, rich, news, featured and entity types snippets. We observed some correlations between overlapping snippets in the same keywords. Results show that commercial keywords do not cause results having rich or entity types snippets, whereas keywords resulting with snippets are not commercial nature. We found that significant number of snippets are scholarly articles and rich cards carousel. We conclude our findings with conclusion and research limitations. |
| Tasks | |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04497v2 |
| https://arxiv.org/pdf/1906.04497v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-snippets-taxonomy-in-web-search-engines |
| Repo | |
| Framework | |
Multi-modal Ensemble Classification for Generalized Zero Shot Learning
| Title | Multi-modal Ensemble Classification for Generalized Zero Shot Learning |
| Authors | Rafael Felix, Michele Sasdelli, Ian Reid, Gustavo Carneiro |
| Abstract | Generalized zero shot learning (GZSL) is defined by a training process containing a set of visual samples from seen classes and a set of semantic samples from seen and unseen classes, while the testing process consists of the classification of visual samples from seen and unseen classes. Current approaches are based on testing processes that focus on only one of the modalities (visual or semantic), even when the training uses both modalities (mostly for regularizing the training process). This under-utilization of modalities, particularly during testing, can hinder the classification accuracy of the method. In addition, we note a scarce attention to the development of learning methods that explicitly optimize a balanced performance of seen and unseen classes. Such issue is one of the reasons behind the vastly superior classification accuracy of seen classes in GZSL methods. In this paper, we mitigate these issues by proposing a new GZSL method based on multi-modal training and testing processes, where the optimization explicitly promotes a balanced classification accuracy between seen and unseen classes. Furthermore, we explore Bayesian inference for the visual and semantic classifiers, which is another novelty of our work in the GZSL framework. Experiments show that our method holds the state of the art (SOTA) results in terms of harmonic mean (H-mean) classification between seen and unseen classes and area under the seen and unseen curve (AUSUC) on several public GZSL benchmarks. |
| Tasks | Bayesian Inference, Zero-Shot Learning |
| Published | 2019-01-15 |
| URL | http://arxiv.org/abs/1901.04623v2 |
| http://arxiv.org/pdf/1901.04623v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-ensemble-classification-for |
| Repo | |
| Framework | |
Semi-Supervised Generative Modeling for Controllable Speech Synthesis
| Title | Semi-Supervised Generative Modeling for Controllable Speech Synthesis |
| Authors | Raza Habib, Soroosh Mariooryad, Matt Shannon, Eric Battenberg, RJ Skerry-Ryan, Daisy Stanton, David Kao, Tom Bagby |
| Abstract | We present a novel generative model that combines state-of-the-art neural text-to-speech (TTS) with semi-supervised probabilistic latent variable models. By providing partial supervision to some of the latent variables, we are able to force them to take on consistent and interpretable purposes, which previously hasn’t been possible with purely unsupervised TTS models. We demonstrate that our model is able to reliably discover and control important but rarely labelled attributes of speech, such as affect and speaking rate, with as little as 1% (30 minutes) supervision. Even at such low supervision levels we do not observe a degradation of synthesis quality compared to a state-of-the-art baseline. Audio samples are available on the web. |
| Tasks | Latent Variable Models, Speech Synthesis |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01709v1 |
| https://arxiv.org/pdf/1910.01709v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-generative-modeling-for |
| Repo | |
| Framework | |
