Paper Group ANR 945
Sublinear Optimal Policy Value Estimation in Contextual Bandits. Privately detecting changes in unknown distributions. Unsupervised Detection of Sub-events in Large Scale Disasters. Time Series Source Separation using Dynamic Mode Decomposition. Unsupervised Visual Feature Learning with Spike-timing-dependent Plasticity: How Far are we from Traditi …
Sublinear Optimal Policy Value Estimation in Contextual Bandits
| Title | Sublinear Optimal Policy Value Estimation in Contextual Bandits |
| Authors | Weihao Kong, Gregory Valiant, Emma Brunskill |
| Abstract | We study the problem of estimating the expected reward of the optimal policy in the stochastic disjoint linear bandit setting. We prove that for certain settings it is possible to obtain an accurate estimate of the optimal policy value even with a number of samples that is sublinear in the number that would be required to \emph{find} a policy that realizes a value close to this optima. We establish nearly matching information theoretic lower bounds, showing that our algorithm achieves near optimal estimation error. Finally, we demonstrate the effectiveness of our algorithm on joke recommendation and cancer inhibition dosage selection problems using real datasets. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06111v2 |
| https://arxiv.org/pdf/1912.06111v2.pdf | |
| PWC | https://paperswithcode.com/paper/sublinear-optimal-policy-value-estimation-in |
| Repo | |
| Framework | |
Privately detecting changes in unknown distributions
| Title | Privately detecting changes in unknown distributions |
| Authors | Rachel Cummings, Sara Krehbiel, Yuliia Lut, Wanrong Zhang |
| Abstract | The change-point detection problem seeks to identify distributional changes in streams of data. Increasingly, tools for change-point detection are applied in settings where data may be highly sensitive and formal privacy guarantees are required, such as identifying disease outbreaks based on hospital records, or IoT devices detecting activity within a home. Differential privacy has emerged as a powerful technique for enabling data analysis while preventing information leakage about individuals. Much of the prior work on change-point detection—including the only private algorithms for this problem—requires complete knowledge of the pre-change and post-change distributions. However, this assumption is not realistic for many practical applications of interest. This work develops differentially private algorithms for solving the change-point problem when the data distributions are unknown. Additionally, the data may be sampled from distributions that change smoothly over time, rather than fixed pre-change and post-change distributions. We apply our algorithms to detect changes in the linear trends of such data streams. Finally, we also provide experimental results to empirically validate the performance of our algorithms. |
| Tasks | Change Point Detection |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01327v2 |
| https://arxiv.org/pdf/1910.01327v2.pdf | |
| PWC | https://paperswithcode.com/paper/privately-detecting-changes-in-unknown |
| Repo | |
| Framework | |
Unsupervised Detection of Sub-events in Large Scale Disasters
| Title | Unsupervised Detection of Sub-events in Large Scale Disasters |
| Authors | Chidubem Arachie, Manas Gaur, Sam Anzaroot, William Groves, Ke Zhang, Alejandro Jaimes |
| Abstract | Social media plays a major role during and after major natural disasters (e.g., hurricanes, large-scale fires, etc.), as people on the ground'' post useful information on what is actually happening. Given the large amounts of posts, a major challenge is identifying the information that is useful and actionable. Emergency responders are largely interested in finding out what events are taking place so they can properly plan and deploy resources. In this paper we address the problem of automatically identifying important sub-events (within a large-scale emergency event’', such as a hurricane). In particular, we present a novel, unsupervised learning framework to detect sub-events in Tweets for retrospective crisis analysis. We first extract noun-verb pairs and phrases from raw tweets as sub-event candidates. Then, we learn a semantic embedding of extracted noun-verb pairs and phrases, and rank them against a crisis-specific ontology. We filter out noisy and irrelevant information then cluster the noun-verb pairs and phrases so that the top-ranked ones describe the most important sub-events. Through quantitative experiments on two large crisis data sets (Hurricane Harvey and the 2015 Nepal Earthquake), we demonstrate the effectiveness of our approach over the state-of-the-art. Our qualitative evaluation shows better performance compared to our baseline. |
| Tasks | |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.13332v1 |
| https://arxiv.org/pdf/1912.13332v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-detection-of-sub-events-in-large |
| Repo | |
| Framework | |
Time Series Source Separation using Dynamic Mode Decomposition
| Title | Time Series Source Separation using Dynamic Mode Decomposition |
| Authors | Arvind Prasadan, Raj Rao Nadakuditi |
| Abstract | The Dynamic Mode Decomposition (DMD) extracted dynamic modes are the non-orthogonal eigenvectors of the matrix that best approximates the one-step temporal evolution of the multivariate samples. In the context of dynamical system analysis, the extracted dynamic modes are a generalization of global stability modes. We apply DMD to a data matrix whose rows are linearly independent, additive mixtures of latent time series. We show that when the latent time series are uncorrelated at a lag of one time-step then, in the large sample limit, the recovered dynamic modes will approximate, up to a column-wise normalization, the columns of the mixing matrix. Thus, DMD is a time series blind source separation algorithm in disguise, but is different from closely related second order algorithms such as the Second-Order Blind Identification (SOBI) method and the Algorithm for Multiple Unknown Signals Extraction (AMUSE). All can unmix mixed stationary, ergodic Gaussian time series in a way that kurtosis-based Independent Components Analysis (ICA) fundamentally cannot. We use our insights on single lag DMD to develop a higher-lag extension, analyze the finite sample performance with and without randomly missing data, and identify settings where the higher lag variant can outperform the conventional single lag variant. We validate our results with numerical simulations, and highlight how DMD can be used in change point detection. |
| Tasks | Change Point Detection, Time Series |
| Published | 2019-03-04 |
| URL | https://arxiv.org/abs/1903.01310v4 |
| https://arxiv.org/pdf/1903.01310v4.pdf | |
| PWC | https://paperswithcode.com/paper/time-series-source-separation-using-dynamic |
| Repo | |
| Framework | |
Unsupervised Visual Feature Learning with Spike-timing-dependent Plasticity: How Far are we from Traditional Feature Learning Approaches?
| Title | Unsupervised Visual Feature Learning with Spike-timing-dependent Plasticity: How Far are we from Traditional Feature Learning Approaches? |
| Authors | Pierre Falez, Pierre Tirilly, Ioan Marius Bilasco, Philippe Devienne, Pierre Boulet |
| Abstract | Spiking neural networks (SNNs) equipped with latency coding and spike-timing dependent plasticity rules offer an alternative to solve the data and energy bottlenecks of standard computer vision approaches: they can learn visual features without supervision and can be implemented by ultra-low power hardware architectures. However, their performance in image classification has never been evaluated on recent image datasets. In this paper, we compare SNNs to auto-encoders on three visual recognition datasets, and extend the use of SNNs to color images. The analysis of the results helps us identify some bottlenecks of SNNs: the limits of on-center/off-center coding, especially for color images, and the ineffectiveness of current inhibition mechanisms. These issues should be addressed to build effective SNNs for image recognition. |
| Tasks | Image Classification |
| Published | 2019-01-14 |
| URL | http://arxiv.org/abs/1901.04392v2 |
| http://arxiv.org/pdf/1901.04392v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-visual-feature-learning-with |
| Repo | |
| Framework | |
BreGMN: scaled-Bregman Generative Modeling Networks
| Title | BreGMN: scaled-Bregman Generative Modeling Networks |
| Authors | Akash Srivastava, Kristjan Greenewald, Farzaneh Mirzazadeh |
| Abstract | The family of f-divergences is ubiquitously applied to generative modeling in order to adapt the distribution of the model to that of the data. Well-definedness of f-divergences, however, requires the distributions of the data and model to overlap completely in every time step of training. As a result, as soon as the support of distributions of data and model contain non-overlapping portions, gradient based training of the corresponding model becomes hopeless. Recent advances in generative modeling are full of remedies for handling this support mismatch problem: key ideas include either modifying the objective function to integral probability measures (IPMs) that are well-behaved even on disjoint probabilities, or optimizing a well-behaved variational lower bound instead of the true objective. We, on the other hand, establish that a complete change of the objective function is unnecessary, and instead an augmentation of the base measure of the problematic divergence can resolve the issue. Based on this observation, we propose a generative model which leverages the class of Scaled Bregman Divergences and generalizes both f-divergences and Bregman divergences. We analyze this class of divergences and show that with the appropriate choice of base measure it can resolve the support mismatch problem and incorporate geometric information. Finally, we study the performance of the proposed method and demonstrate promising results on MNIST, CelebA and CIFAR-10 datasets. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://arxiv.org/abs/1906.00313v1 |
| https://arxiv.org/pdf/1906.00313v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600313 |
| Repo | |
| Framework | |
Adaptive Regret of Convex and Smooth Functions
| Title | Adaptive Regret of Convex and Smooth Functions |
| Authors | Lijun Zhang, Tie-Yan Liu, Zhi-Hua Zhou |
| Abstract | We investigate online convex optimization in changing environments, and choose the adaptive regret as the performance measure. The goal is to achieve a small regret over every interval so that the comparator is allowed to change over time. Different from previous works that only utilize the convexity condition, this paper further exploits smoothness to improve the adaptive regret. To this end, we develop novel adaptive algorithms for convex and smooth functions, and establish problem-dependent regret bounds over any interval. Our regret bounds are comparable to existing results in the worst case, and become much tighter when the comparator has a small loss. |
| Tasks | |
| Published | 2019-04-26 |
| URL | https://arxiv.org/abs/1904.11681v3 |
| https://arxiv.org/pdf/1904.11681v3.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-regret-of-convex-and-smooth |
| Repo | |
| Framework | |
Detecting Overfitting via Adversarial Examples
| Title | Detecting Overfitting via Adversarial Examples |
| Authors | Roman Werpachowski, András György, Csaba Szepesvári |
| Abstract | The repeated community-wide reuse of test sets in popular benchmark problems raises doubts about the credibility of reported test-error rates. Verifying whether a learned model is overfitted to a test set is challenging as independent test sets drawn from the same data distribution are usually unavailable, while other test sets may introduce a distribution shift. We propose a new hypothesis test that uses only the original test data to detect overfitting. It utilizes a new unbiased error estimate that is based on adversarial examples generated from the test data and importance weighting. Overfitting is detected if this error estimate is sufficiently different from the original test error rate. We develop a specialized variant of our test for multiclass image classification, and apply it to testing overfitting of recent models to the popular ImageNet benchmark. Our method correctly indicates overfitting of the trained model to the training set, but is not able to detect any overfitting to the test set, in line with other recent work on this topic. |
| Tasks | Image Classification |
| Published | 2019-03-06 |
| URL | https://arxiv.org/abs/1903.02380v2 |
| https://arxiv.org/pdf/1903.02380v2.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-overfitting-via-adversarial |
| Repo | |
| Framework | |
World Programs for Model-Based Learning and Planning in Compositional State and Action Spaces
| Title | World Programs for Model-Based Learning and Planning in Compositional State and Action Spaces |
| Authors | Marwin H. S. Segler |
| Abstract | Some of the most important tasks take place in environments which lack cheap and perfect simulators, thus hampering the application of model-free reinforcement learning (RL). While model-based RL aims to learn a dynamics model, in a more general case the learner does not know a priori what the action space is. Here we propose a formalism where the learner induces a world program by learning a dynamics model and the actions in graph-based compositional environments by observing state-state transition examples. Then, the learner can perform RL with the world program as the simulator for complex planning tasks. We highlight a recent application, and propose a challenge for the community to assess world program-based planning. |
| Tasks | |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.13007v1 |
| https://arxiv.org/pdf/1912.13007v1.pdf | |
| PWC | https://paperswithcode.com/paper/world-programs-for-model-based-learning-and |
| Repo | |
| Framework | |
Mask-Guided Portrait Editing with Conditional GANs
| Title | Mask-Guided Portrait Editing with Conditional GANs |
| Authors | Shuyang Gu, Jianmin Bao, Hao Yang, Dong Chen, Fang Wen, Lu Yuan |
| Abstract | Portrait editing is a popular subject in photo manipulation. The Generative Adversarial Network (GAN) advances the generating of realistic faces and allows more face editing. In this paper, we argue about three issues in existing techniques: diversity, quality, and controllability for portrait synthesis and editing. To address these issues, we propose a novel end-to-end learning framework that leverages conditional GANs guided by provided face masks for generating faces. The framework learns feature embeddings for every face component (e.g., mouth, hair, eye), separately, contributing to better correspondences for image translation, and local face editing. With the mask, our network is available to many applications, like face synthesis driven by mask, face Swap+ (including hair in swapping), and local manipulation. It can also boost the performance of face parsing a bit as an option of data augmentation. |
| Tasks | Data Augmentation, Face Generation |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10346v1 |
| https://arxiv.org/pdf/1905.10346v1.pdf | |
| PWC | https://paperswithcode.com/paper/mask-guided-portrait-editing-with-conditional-1 |
| Repo | |
| Framework | |
Multi-Prototype Networks for Unconstrained Set-based Face Recognition
| Title | Multi-Prototype Networks for Unconstrained Set-based Face Recognition |
| Authors | Jian Zhao, Jianshu Li, Xiaoguang Tu, Fang Zhao, Yuan Xin, Junliang Xing, Hengzhu Liu, Shuicheng Yan, Jiashi Feng |
| Abstract | In this paper, we study the challenging unconstrained set-based face recognition problem where each subject face is instantiated by a set of media (images and videos) instead of a single image. Naively aggregating information from all the media within a set would suffer from the large intra-set variance caused by heterogeneous factors (e.g., varying media modalities, poses and illuminations) and fail to learn discriminative face representations. A novel Multi-Prototype Network (MPNet) model is thus proposed to learn multiple prototype face representations adaptively from the media sets. Each learned prototype is representative for the subject face under certain condition in terms of pose, illumination and media modality. Instead of handcrafting the set partition for prototype learning, MPNet introduces a Dense SubGraph (DSG) learning sub-net that implicitly untangles inconsistent media and learns a number of representative prototypes. Qualitative and quantitative experiments clearly demonstrate superiority of the proposed model over state-of-the-arts. |
| Tasks | Face Recognition |
| Published | 2019-02-13 |
| URL | http://arxiv.org/abs/1902.04755v4 |
| http://arxiv.org/pdf/1902.04755v4.pdf | |
| PWC | https://paperswithcode.com/paper/multi-prototype-networks-for-unconstrained |
| Repo | |
| Framework | |
Learning from both experts and data
| Title | Learning from both experts and data |
| Authors | Rémi Besson, Erwan Le Pennec, Stéphanie Allassonnière |
| Abstract | In this work we study the problem of inferring a discrete probability distribution using both expert knowledge and empirical data. This is an important issue for many applications where the scarcity of data prevents a purely empirical approach. In this context, it is common to rely first on an initial domain knowledge a priori before proceeding to an online data acquisition. We are particularly interested in the intermediate regime where we do not have enough data to do without the initial expert a priori of the experts, but enough to correct it if necessary. We present here a novel way to tackle this issue with a method providing an objective way to choose the weight to be given to experts compared to data. We show, both empirically and theoretically, that our proposed estimator is always more efficient than the best of the two models (expert or data) within a constant. |
| Tasks | |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.09043v2 |
| https://arxiv.org/pdf/1910.09043v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-both-experts-and-data |
| Repo | |
| Framework | |
Modeling Event Background for If-Then Commonsense Reasoning Using Context-aware Variational Autoencoder
| Title | Modeling Event Background for If-Then Commonsense Reasoning Using Context-aware Variational Autoencoder |
| Authors | Li Du, Xiao Ding, Ting Liu, Zhongyang Li |
| Abstract | Understanding event and event-centered commonsense reasoning are crucial for natural language processing (NLP). Given an observed event, it is trivial for human to infer its intents and effects, while this type of If-Then reasoning still remains challenging for NLP systems. To facilitate this, a If-Then commonsense reasoning dataset Atomic is proposed, together with an RNN-based Seq2Seq model to conduct such reasoning. However, two fundamental problems still need to be addressed: first, the intents of an event may be multiple, while the generations of RNN-based Seq2Seq models are always semantically close; second, external knowledge of the event background may be necessary for understanding events and conducting the If-Then reasoning. To address these issues, we propose a novel context-aware variational autoencoder effectively learning event background information to guide the If-Then reasoning. Experimental results show that our approach improves the accuracy and diversity of inferences compared with state-of-the-art baseline methods. |
| Tasks | |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08824v3 |
| https://arxiv.org/pdf/1909.08824v3.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-event-background-for-if-then |
| Repo | |
| Framework | |
The performance evaluation of Multi-representation in the Deep Learning models for Relation Extraction Task
| Title | The performance evaluation of Multi-representation in the Deep Learning models for Relation Extraction Task |
| Authors | Jefferson A. Peña Torres, Raul Ernesto Gutierrez, Victor A. Bucheli, Fabio A. Gonzalez O |
| Abstract | Single implementing, concatenating, adding or replacing of the representations has yielded significant improvements on many NLP tasks. Mainly in Relation Extraction where static, contextualized and others representations that are capable of explaining word meanings through the linguistic features that these incorporates. In this work addresses the question of how is improved the relation extraction using different types of representations generated by pretrained language representation models. We benchmarked our approach using popular word representation models, replacing and concatenating static, contextualized and others representations of hand-extracted features. The experiments show that representation is a crucial element to choose when DL approach is applied. Word embeddings from Flair and BERT can be well interpreted by a deep learning model for RE task, and replacing static word embeddings with contextualized word representations could lead to significant improvements. While, the hand-created representations requires is time-consuming and not is ensure a improve in combination with others representations. |
| Tasks | Relation Extraction, Word Embeddings |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.08290v1 |
| https://arxiv.org/pdf/1912.08290v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-performance-evaluation-of-multi |
| Repo | |
| Framework | |
Segmentation of Multimodal Myocardial Images Using Shape-Transfer GAN
| Title | Segmentation of Multimodal Myocardial Images Using Shape-Transfer GAN |
| Authors | Xumin Tao, Hongrong Wei, Wufeng Xue, Dong Ni |
| Abstract | Myocardium segmentation of late gadolinium enhancement (LGE) Cardiac MR images is important for evaluation of infarction regions in clinical practice. The pathological myocardium in LGE images presents distinctive brightness and textures compared with the healthy tissues, making it much more challenging to be segment. Instead, the balanced-Steady State Free Precession (bSSFP) cine images show clearly boundaries and can be easily segmented. Given this fact, we propose a novel shape-transfer GAN for LGE images, which can 1) learn to generate realistic LGE images from bSSFP with the anatomical shape preserved, and 2) learn to segment the myocardium of LGE images from these generated images. It’s worth to note that no segmentation label of the LGE images is used during this procedure. We test our model on dataset from the Multi-sequence Cardiac MR Segmentation Challenge. The results show that the proposed Shape-Transfer GAN can achieve accurate myocardium masks of LGE images. |
| Tasks | |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05094v1 |
| https://arxiv.org/pdf/1908.05094v1.pdf | |
| PWC | https://paperswithcode.com/paper/segmentation-of-multimodal-myocardial-images |
| Repo | |
| Framework | |
