Latest in cs.lg
total 12534took 0.23s
Bayesian inference for bivariate ranksFeb 09 2018A recommender system based on ranks is proposed, where an expert's ranking of a set of objects and a user's ranking of a subset of those objects are combined to make a prediction of the user's ranking of all objects. The rankings are assumed to be induced ... More Algorithmic Bidding for Virtual Trading in Electricity MarketsFeb 08 2018We consider the problem of optimal bidding for virtual trading in two-settlement electricity markets. A virtual trader aims to arbitrage on the differences between day-ahead and real-time market prices; both prices, however, are random and unknown to ... More Learning Sparse Wavelet RepresentationsFeb 08 2018In this work we propose a method for learning wavelet filters directly from data. We accomplish this by framing the discrete wavelet transform as a modified convolutional neural network. We introduce an autoencoder wavelet transform network that is trained ... More Online Learning: A Comprehensive SurveyFeb 08 2018Online learning represents an important family of machine learning algorithms, in which a learner attempts to resolve an online prediction (or any type of decision-making) task by learning a model/hypothesis from a sequence of data instances one at a ... More Neural Network Renormalization GroupFeb 08 2018We present a variational renormalization group approach using deep generative model composed of bijectors. The model can learn hierarchical transformations between physical variables and renormalized collective variables. It can directly generate statistically ... More Transductive Adversarial Networks (TAN)Feb 08 2018Transductive Adversarial Networks (TAN) is a novel domain-adaptation machine learning framework that is designed for learning a conditional probability distribution on unlabelled input data in a target domain, while also only having access to: (1) easily ... More Learning Inductive Biases with Simple Neural NetworksFeb 08 2018People use rich prior knowledge about the world in order to efficiently learn new concepts. These priors - also known as "inductive biases" - pertain to the space of internal models considered by a learner, and they help the learner make inferences that ... More Gradient conjugate priors and deep neural networksFeb 07 2018The paper deals with learning the probability distribution of the observed data by artificial neural networks. We suggest a so-called gradient conjugate prior (GCP) update appropriate for neural networks, which is a modification of the classical Bayesian ... More VISER: Visual Self-RegularizationFeb 07 2018In this work, we propose the use of large set of unlabeled images as a source of regularization data for learning robust visual representation. Given a visual model trained by a labeled dataset in a supervised fashion, we augment our training samples ... More Semi-Amortized Variational AutoencodersFeb 07 2018Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE), recent empirical work suggests ... More Learning One Convolutional Layer with Overlapping PatchesFeb 07 2018We give the first provably efficient algorithm for learning a one hidden layer convolutional network with respect to a general class of (potentially overlapping) patches. Additionally, our algorithm requires only mild conditions on the underlying distribution. ... More Spectral Learning of Binomial HMMs for DNA Methylation DataFeb 07 2018We consider learning parameters of Binomial Hidden Markov Models, which may be used to model DNA methylation data. The standard algorithm for the problem is EM, which is computationally expensive for sequences of the scale of the mammalian genome. Recently ... More Universal Deep Neural Network CompressionFeb 07 2018Compression of deep neural networks (DNNs) for memory- and computation-efficient compact feature representations becomes a critical problem particularly for deployment of DNNs on resource-limited platforms. In this paper, we investigate lossy compression ... More Granger-causal Attentive Mixtures of ExpertsFeb 06 2018Several methods have recently been proposed to detect salient input features for outputs of neural networks. Those methods offer a qualitative glimpse at feature importance, but they fall short of providing quantifiable attributions that can be compared ... More Système de traduction automatique statistique Anglais-ArabeFeb 06 2018Machine translation (MT) is the process of translating text written in a source language into text in a target language. In this article, we present our English-Arabic statistical machine translation system. First, we present the general process for setting ... More Improving Variational Encoder-Decoders in Dialogue GenerationFeb 06 2018Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and decoding, yielding ... More A Survey Of Methods For Explaining Black Box ModelsFeb 06 2018In the last years many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports ... More Texygen: A Benchmarking Platform for Text Generation ModelsFeb 06 2018We introduce Texygen, a benchmarking platform to support research on open-domain text generation models. Texygen has not only implemented a majority of text generation models, but also covered a set of metrics that evaluate the diversity, the quality ... More Near-Optimal Coresets of Kernel Density EstimatesFeb 06 2018We construct near-optimal coresets for kernel density estimate for points in $\mathbb{R^d}$ when the kernel is positive definite. Specifically we show a polynomial time construction for a coreset of size $O(\sqrt{d\log (1/\epsilon)}/\epsilon)$, and we ... More Re-Weighted Learning for Sparsifying Deep Neural NetworksFeb 05 2018This paper addresses the topic of sparsifying deep neural networks (DNN's). While DNN's are powerful models that achieve state-of-the-art performance on a large number of tasks, the large number of model parameters poses serious storage and computational ... More Non-Gaussian information from weak lensing data via deep learningFeb 04 2018Feb 06 2018Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the lensing field. Here we train and ... More Representation Learning for Resource Usage PredictionFeb 02 2018Creating a model of a computer system that can be used for tasks such as predicting future resource usage and detecting anomalies is a challenging problem. Most current systems rely on heuristics and overly simplistic assumptions about the workloads and ... More Scalable Lévy Process Priors for Spectral Kernel LearningFeb 02 2018Gaussian processes are rich distributions over functions, with generalization properties determined by a kernel function. When used for long-range extrapolation, predictions are particularly sensitive to the choice of kernel parameters. It is therefore ... More Kernel Distillation for Gaussian ProcessesJan 31 2018Gaussian processes (GPs) are flexible models that can capture complex structure in large-scale dataset due to their non-parametric nature. However, the usage of GPs in real-world application is limited due to their high computational cost at inference ... More The Intriguing Properties of Model ExplanationsJan 30 2018Linear approximations to the decision boundary of a complex model have become one of the most popular tools for interpreting predictions. In this paper, we study such linear explanations produced either post-hoc by a few recent methods or generated along ... More Nonlinear Dimensionality Reduction on GraphsJan 29 2018In this era of data deluge, many signal processing and machine learning tasks are faced with high-dimensional datasets, including images, videos, as well as time series generated from social, commercial and brain network interactions. Their efficient ... More Learning Symmetry and Low-energy LocomotionJan 24 2018Jan 25 2018Learning locomotion skills is a challenging problem. To generate realistic and smooth locomotion, existing methods use motion capture, finite state machines or morphology-specific knowledge to guide the motion generation algorithms. Deep reinforcement ... More Intrinsic dimension of concept latticesJan 24 2018Geometric analysis is a very capable theory to understand the influence of the high dimensionality of the input data in machine learning (ML) and knowledge discovery (KD). With our approach we can assess how far the application of a specific KD/ML-algorithm ... More Scalable and accurate deep learning for electronic health recordsJan 24 2018Jan 26 2018Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve healthcare quality. Constructing predictive statistical models typically requires extraction of curated predictor variables from normalized ... More MaskGAN: Better Text Generation via Filling in the ______Jan 23 2018Neural text generation models are often autoregressive language models or seq2seq models. These models generate text by sampling words sequentially, with each word conditioned on the previous word, and are state-of-the-art for several machine translation ... More Offline A/B testing for Recommender SystemsJan 22 2018Before A/B testing online a new version of a recommender system, it is usual to perform some offline evaluations on historical data. We focus on evaluation methods that compute an estimator of the potential uplift in revenue that could generate this new ... More A Deep Reinforcement Learning Chatbot (Short Version)Jan 20 2018We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both ... More An Overview of Machine TeachingJan 18 2018In this paper we try to organize machine teaching as a coherent set of ideas. Each idea is presented as varying along a dimension. The collection of dimensions then form the problem space of machine teaching, such that existing teaching problems can be ... More Time Series Segmentation through Automatic Feature LearningJan 16 2018Jan 26 2018Internet of things (IoT) applications have become increasingly popular in recent years, with applications ranging from building energy monitoring to personal health tracking and activity recognition. In order to leverage these data, automatic knowledge ... More A3T: Adversarially Augmented Adversarial TrainingJan 12 2018Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification models, including ... More Approximate FPGA-based LSTMs under Computation Time ConstraintsJan 07 2018Recurrent Neural Networks and in particular Long Short-Term Memory (LSTM) networks have demonstrated state-of-the-art accuracy in several emerging Artificial Intelligence tasks. However, the models are becoming increasingly demanding in terms of computational ... More Deep Learning: A Critical AppraisalJan 02 2018Although deep learning has historical roots going back decades, neither the term "deep learning" nor the approach was popular just over five years ago, when the field was reignited by papers such as Krizhevsky, Sutskever and Hinton's now classic (2012) ... More Kernel Robust Bias-Aware Prediction under Covariate ShiftDec 28 2017Under covariate shift, training (source) data and testing (target) data differ in input space distribution, but share the same conditional label distribution. This poses a challenging machine learning task. Robust Bias-Aware (RBA) prediction provides ... More Directional Statistics and Filtering Using libDirectionalDec 28 2017In this paper, we present libDirectional, a MATLAB library for directional statistics and directional estimation. It supports a variety of commonly used distributions on the unit circle, such as the von Mises, wrapped normal, and wrapped Cauchy distributions. ... More The information bottleneck and geometric clusteringDec 27 2017The information bottleneck (IB) approach to clustering takes a joint distribution $P\!\left(X,Y\right)$ and maps the data $X$ to cluster labels $T$ which retain maximal information about $Y$ (Tishby et al., 1999). This objective results in an algorithm ... More Dropout Feature Ranking for Deep Learning ModelsDec 22 2017Deep neural networks are a promising technology achieving state-of-the-art results in biological and healthcare domains. Unfortunately, DNNs are notorious for their non-interpretability. Clinicians are averse to black boxes and thus interpretability is ... More Note on Attacking Object Detectors with Adversarial StickersDec 21 2017Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable to adversarial examples. These adversarial inputs are created such that, ... More