Latest in cs.lg
total 36380took 0.11s
Reweighted Expectation MaximizationJun 13 2019Training deep generative models with maximum likelihood remains a challenge. The typical workaround is to use variational inference (VI) and maximize a lower bound to the log marginal likelihood of the data. Variational auto-encoders (VAEs) adopt this ... More The Communication Complexity of OptimizationJun 13 2019We consider the communication complexity of a number of distributed optimization problems. We start with the problem of solving a linear system. Suppose there is a coordinator together with $s$ servers $P_1, \ldots, P_s$, the $i$-th of which holds a subset ... More Kernel and Deep Regimes in Overparametrized ModelsJun 13 2019A recent line of work studies overparametrized neural networks in the ``kernel regime,'' i.e.~when the network behaves during training as a kernelized linear predictor, and thus training with gradient descent has the effect of finding the minimum RKHS ... More Robust Regression for Safe Exploration in ControlJun 13 2019We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from an operating environment to learn an optimal controller. A central challenge in this setting is how to quantify uncertainty ... More Lower Bounds for Adversarially Robust PAC LearningJun 13 2019In this work, we initiate a formal study of probably approximately correct (PAC) learning under evasion attacks, where the adversary's goal is to \emph{misclassify} the adversarially perturbed sample point $\widetilde{x}$, i.e., $h(\widetilde{x})\neq ... More Deep Reinforcement Learning for Cyber SecurityJun 13 2019The scale of Internet-connected systems has increased considerably, and these systems are being exposed to cyber attacks more than ever. The complexity and dynamics of cyber attacks require protecting mechanisms to be responsive, adaptive, and large-scale. ... More Nonlinear System Identification via Tensor CompletionJun 13 2019Function approximation from input and output data pairs constitutes a fundamental problem in supervised learning. Deep neural networks are currently the most popular method for learning to mimic the input-output relationship of a generic nonlinear system, ... More Iterative subtraction method for Feature RankingJun 13 2019Training features used to analyse physical processes are often highly correlated and determining which ones are most important for the classification is a non-trivial tasks. For the use case of a search for a top-quark pair produced in association with ... More Training Neural Networks for and by InterpolationJun 13 2019The majority of modern deep learning models are able to interpolate the data: the empirical loss can be driven near zero on all samples simultaneously. In this work, we explicitly exploit this interpolation property for the design of a new optimization ... More $c^+$GAN: Complementary Fashion Item RecommendationJun 13 2019We present a conditional generative adversarial model to draw realistic samples from paired fashion clothing distribution and provide real samples to pair with arbitrary fashion units. More concretely, given an image of a shirt, obtained from a fashion ... More Selective prediction-set models with coverage guaranteesJun 13 2019Though black-box predictors are state-of-the-art for many complex tasks, they often fail to properly quantify predictive uncertainty and may provide inappropriate predictions for unfamiliar data. Instead, we can learn more reliable models by letting them ... More Reinforcement Learning of Spatio-Temporal Point ProcessesJun 13 2019Spatio-temporal event data is ubiquitous in various applications, such as social media, crime events, and electronic health records. Spatio-temporal point processes offer a versatile framework for modeling such event data, as it can jointly capture spatial ... More Random Tessellation ForestsJun 13 2019Space partitioning methods such as random forests and the Mondrian process are powerful machine learning methods for multi-dimensional and relational data, and are based on recursively cutting a domain. The flexibility of these methods is often limited ... More Neural Arabic Question AnsweringJun 12 2019This paper tackles the problem of open domain factual Arabic question answering (QA) using Wikipedia as our knowledge source. This constrains the answer of any question to be a span of text in Wikipedia. Open domain QA for Arabic entails three challenges: ... More Competing Bandits in Matching MarketsJun 12 2019Stable matching, a classical model for two-sided markets, has long been studied with little consideration for how each side's preferences are learned. With the advent of massive online markets powered by data-driven matching platforms, it has become necessary ... More Optimal low rank tensor recoveryJun 12 2019We investigate the sample size requirement for exact recovery of a high order tensor of low rank from a subset of its entries. In the Tucker decomposition framework, we show that the Riemannian optimization algorithm with initial value obtained from a ... More Efficient Exploration via State Marginal MatchingJun 12 2019To solve tasks with sparse rewards, reinforcement learning algorithms must be equipped with suitable exploration techniques. However, it is unclear what underlying objective is being optimized by existing exploration algorithms, or how they can be altered ... More Artificial Intelligence Enabled Material Behavior PredictionJun 12 2019Artificial Intelligence and Machine Learning algorithms have considerable potential to influence the prediction of material properties. Additive materials have a unique property prediction challenge in the form of surface roughness effects on fatigue ... More GluonTS: Probabilistic Time Series Models in PythonJun 12 2019We introduce Gluon Time Series (GluonTS)\footnote{\url{https://gluon-ts.mxnet.io}}, a library for deep-learning-based time series modeling. GluonTS simplifies the development of and experimentation with time series models for common tasks such as forecasting ... More Image-Adaptive GAN based ReconstructionJun 12 2019In the recent years, there has been a significant improvement in the quality of samples produced by (deep) generative models such as variational auto-encoders and generative adversarial networks. However, the representation capabilities of these methods ... More Representation Learning for Words and EntitiesJun 12 2019This thesis presents new methods for unsupervised learning of distributed representations of words and entities from text and knowledge bases. The first algorithm presented in the thesis is a multi-view algorithm for learning representations of words ... More Multitask Learning for Network Traffic ClassificationJun 12 2019Traffic classification has various applications in today's Internet, from resource allocation, billing and QoS purposes in ISPs to firewall and malware detection in clients. Classical machine learning algorithms and deep learning models have been widely ... More Bootstrapping Upper Confidence BoundJun 12 2019Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confidence bounds are typically built upon various concentration inequalities, ... More Continual and Multi-Task Architecture SearchJun 12 2019Architecture search is the process of automatically learning the neural model or cell structure that best suits the given task. Recently, this approach has shown promising performance improvements (on language modeling and image classification) with reasonable ... More A Model to Search for Synthesizable MoleculesJun 12 2019Deep generative models are able to suggest new organic molecules by generating strings, trees, and graphs representing their structure. While such models allow one to generate molecules with desirable properties, they give no guarantees that the molecules ... More Is Deep Learning an RG Flow?Jun 12 2019Although there has been a rapid development of practical applications, theoretical explanations of deep learning are in their infancy. A possible starting point suggests that deep learning performs a sophisticated coarse graining. Coarse graining is the ... More Sorted Top-k in RoundsJun 12 2019We consider the sorted top-$k$ problem whose goal is to recover the top-$k$ items with the correct order out of $n$ items using pairwise comparisons. In many applications, multiple rounds of interaction can be costly. We restrict our attention to algorithms ... More Warping Resilient Time Series EmbeddingsJun 12 2019Time series are ubiquitous in real world problems and computing distance between two time series is often required in several learning tasks. Computing similarity between time series by ignoring variations in speed or warping is often encountered and ... More Task Agnostic Continual Learning via Meta LearningJun 12 2019While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that studies learning under non-stationary distribution is provided by continual ... More Boosting Few-Shot Visual Learning with Self-SupervisionJun 12 2019Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to recognize patterns ... More Parameterized Structured Pruning for Deep Neural NetworksJun 12 2019As a result of the growing size of Deep Neural Networks (DNNs), the gap to hardware capabilities in terms of memory and compute increases. To effectively compress DNNs, quantization and connection pruning are usually considered. However, unconstrained ... More Secure Federated Matrix FactorizationJun 12 2019To protect user privacy and meet law regulations, federated (machine) learning is obtaining vast interests in recent years. The key principle of federated learning is training a machine learning model without needing to know each user's personal raw private ... More Deep Smoothing of the Implied Volatility SurfaceJun 12 2019We present an artificial neural network (ANN) approach to value financial derivatives. Atypically to standard ANN applications, practitioners equally use option pricing models to validate market prices and to infer unobserved prices. Importantly, models ... More Unified Semantic Parsing with Weak SupervisionJun 12 2019Semantic parsing over multiple knowledge bases enables a parser to exploit structural similarities of programs across the multiple domains. However, the fundamental challenge lies in obtaining high-quality annotations of (utterance, program) pairs across ... More Decoupling Gating from LinearityJun 12 2019ReLU neural-networks have been in the focus of many recent theoretical works, trying to explain their empirical success. Nonetheless, there is still a gap between current theoretical results and empirical observations, even in the case of shallow (one ... More Fast Task Inference with Variational Intrinsic Successor FeaturesJun 12 2019It has been established that diverse behaviors spanning the controllable subspace of an Markov decision process can be trained by rewarding a policy for being distinguishable from other policies \citep{gregor2016variational, eysenbach2018diversity, warde2018unsupervised}. ... More Who Will Win It? An In-game Win Probability Model for FootballJun 12 2019In-game win probability is a statistical metric that provides a sports team's likelihood of winning at any given point in a game, based on the performance of historical teams in the same situation. In-game win-probability models have been extensively ... More Unsupervised Question Answering by Cloze TranslationJun 12 2019Obtaining training data for Question Answering (QA) is time-consuming and resource-intensive, and existing QA datasets are only available for limited domains and languages. In this work, we explore to what extent high quality training data is actually ... More A Structured Learning Approach to Temporal Relation ExtractionJun 12 2019Identifying temporal relations between events is an essential step towards natural language understanding. However, the temporal relation between two events in a story depends on, and is often dictated by, relations among other events. Consequently, effectively ... More Partial Or Complete, That's The QuestionJun 12 2019For many structured learning tasks, the data annotation process is complex and costly. Existing annotation schemes usually aim at acquiring completely annotated structures, under the common perception that partial structures are of low quality and could ... More Relative Hausdorff Distance for Network AnalysisJun 12 2019Similarity measures are used extensively in machine learning and data science algorithms. The newly proposed graph Relative Hausdorff (RH) distance is a lightweight yet nuanced similarity measure for quantifying the closeness of two graphs. In this work ... More Non-Parametric Calibration for ClassificationJun 12 2019Many applications for classification methods not only require high accuracy but also reliable estimation of predictive uncertainty. However, while many current classification frameworks, in particular deep neural network architectures, provide very good ... More SPoC: Search-based Pseudocode to CodeJun 12 2019We consider the task of mapping pseudocode to long programs that are functionally correct. Given test cases as a mechanism to validate programs, we search over the space of possible translations of the pseudocode to find a program that passes the validation. ... More Coresets for Gaussian Mixture Models of Any ShapeJun 12 2019An $\varepsilon$-coreset for a given set $D$ of $n$ points, is usually a small weighted set, such that querying the coreset \emph{provably} yields a $(1+\varepsilon)$-factor approximation to the original (full) dataset, for a given family of queries. ... More Compressive Hyperspherical Energy MinimizationJun 12 2019Recent work on minimum hyperspherical energy (MHE) has demonstrated its potential in regularizing neural networks and improving their generalization. MHE was inspired by the Thomson problem in physics, where the distribution of multiple propelling electrons ... More Using Small Proxy Datasets to Accelerate Hyperparameter SearchJun 12 2019One of the biggest bottlenecks in a machine learning workflow is waiting for models to train. Depending on the available computing resources, it can take days to weeks to train a neural network on a large dataset with many classes such as ImageNet. For ... More Multiple instance learning with graph neural networksJun 12 2019Multiple instance learning (MIL) aims to learn the mapping between a bag of instances and the bag-level label. In this paper, we propose a new end-to-end graph neural network (GNN) based algorithm for MIL: we treat each bag as a graph and use GNN to learn ... More Communication-Efficient Accurate Statistical EstimationJun 12 2019When the data are stored in a distributed manner, direct application of traditional statistical inference procedures is often prohibitive due to communication cost and privacy concerns. This paper develops and investigates two Communication-Efficient ... More On regularization for a convolutional kernel in neural networksJun 12 2019Convolutional neural network is a very important model of deep learning. It can help avoid the exploding/vanishing gradient problem and improve the generalizability of a neural network if the singular values of the Jacobian of a layer are bounded around ... More Statistical guarantees for local graph clusteringJun 11 2019Local graph clustering methods aim to find small clusters in very large graphs. These methods take as input a graph and a seed node, and they return as output a good cluster in a running time that depends on the size of the output cluster but that is ... More Reinforcement Learning for Integer Programming: Learning to CutJun 11 2019Integer programming (IP) is a general optimization framework widely applicable to a variety of unstructured and structured problems arising in, e.g., scheduling, production planning, and graph optimization. As IP models many provably hard to solve problems, ... More Task-Aware Deep Sampling for Feature GenerationJun 11 2019The human ability to imagine the variety of appearances of novel objects based on past experience is crucial for quickly learning novel visual concepts based on few examples. Endowing machines with a similar ability to generate feature distributions for ... More Discrepancy, Coresets, and Sketches in Machine LearningJun 11 2019This paper defines the notion of class discrepancy for families of functions. It shows that low discrepancy classes admit small offline and streaming coresets. We provide general techniques for bounding the class discrepancy of machine learning problems. ... More