Latest in cs.lg
total 30027took 0.15s
PLUME: Polyhedral Learning Using Mixture of ExpertsApr 22 2019In this paper, we propose a novel mixture of expert architecture for learning polyhedral classifiers. We learn the parameters of the classifierusing an expectation maximization algorithm. Wederive the generalization bounds of the proposedapproach. Through ... More Tracking and Improving Information in the Service of FairnessApr 22 2019As algorithmic prediction systems have become widespread, fears that these systems may inadvertently discriminate against members of underrepresented populations have grown. With the goal of understanding fundamental principles that underpin the growing ... More Adversarial Dropout for Recurrent Neural NetworksApr 22 2019Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs). Dropout techniques for RNNs were introduced to respond to these demands, but we conjecture ... More hf0: A hybrid pitch extraction method for multimodal voiceApr 22 2019Pitch or fundamental frequency (f0) extraction is a fundamental problem studied extensively for its potential applications in speech and clinical applications. In literature, explicit mode specific (modal speech or singing voice or emotional/ expressive ... More TiK-means: $K$-means clustering for skewed groupsApr 21 2019The $K$-means algorithm is extended to allow for partitioning of skewed groups. Our algorithm is called TiK-Means and contributes a $K$-means type algorithm that assigns observations to groups while estimating their skewness-transformation parameters. ... More Obfuscation for Privacy-preserving Syntactic ParsingApr 21 2019The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural language data, ... More Language Models with TransformersApr 20 2019The Transformer architecture is superior to RNN-based models in computational efficiency. Recently, GPT and BERT demonstrate the efficacy of Transformer models on various NLP tasks using pre-trained language models on large-scale corpora. Surprisingly, ... More Waterfall Bandits: Learning to Sell Ads OnlineApr 20 2019A popular approach to selling online advertising is by a waterfall, where a publisher makes sequential price offers to ad networks for an inventory, and chooses the winner in that order. The publisher picks the order and prices to maximize her revenue. ... More Mining Rules Incrementally over Large Knowledge BasesApr 20 2019Multiple web-scale Knowledge Bases, e.g., Freebase, YAGO, NELL, have been constructed using semi-supervised or unsupervised information extraction techniques and many of them, despite their large sizes, are continuously growing. Much research effort has ... More Repurposing Entailment for Multi-Hop Question Answering TasksApr 20 2019Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning with multiple sentences, it remains unclear how best to ... More On the Convergence of Adam and BeyondApr 19 2019Several recently proposed stochastic optimization methods that have been successfully used in training deep networks such as RMSProp, Adam, Adadelta, Nadam are based on using gradient updates scaled by square roots of exponential moving averages of squared ... More Transfer Entropy: where Shannon meets TuringApr 19 2019Transfer Entropy is capable of capturing non-linear source-destination relations between multivariate time-series. It is a measure of association between source data that are transformed into destination data via a set of linear transformations between ... More Knowledge Distillation via Route Constrained OptimizationApr 19 2019Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily learned by a miniaturized ... More Simple yet efficient real-time pose-based action recognitionApr 19 2019Recognizing human actions is a core challenge for autonomous systems as they directly share the same space with humans. Systems must be able to recognize and assess human actions in real-time. In order to train corresponding data-driven algorithms, a ... More SelFlow: Self-Supervised Learning of Optical FlowApr 19 2019We present a self-supervised learning approach for optical flow. Our method distills reliable flow estimations from non-occluded pixels, and uses these predictions as ground truth to learn optical flow for hallucinated occlusions. We further design a ... More SCANN: Synthesis of Compact and Accurate Neural NetworksApr 19 2019Artificial neural networks (ANNs) have become the driving force behind recent artificial intelligence (AI) research. An important problem with implementing a neural network is the design of its architecture. Typically, such an architecture is obtained ... More Hierarchical Meta LearningApr 19 2019Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks share the same out-put structure. To obtain a meta model applicable to the ... More When is a Prediction Knowledge?Apr 18 2019Within Reinforcement Learning, there is a growing collection of research which aims to express all of an agent's knowledge of the world through predictions about sensation, behaviour, and time. This work can be seen not only as a collection of architectural ... More Playgol: learning programs through playApr 18 2019Children learn though play. We introduce the analogous idea of learning programs through play. In this approach, a program induction system (the learner) is given a set of tasks and initial background knowledge. Before solving the tasks, the learner enters ... More Physical Symmetries Embedded in Neural NetworksApr 18 2019Neural networks are a central technique in machine learning. Recent years have seen a wave of interest in applying neural networks to physical systems for which the governing dynamics are known and expressed through differential equations. Two fundamental ... More Towards VQA Models that can ReadApr 18 2019Studies have shown that a dominant class of questions asked by visually impaired users on images of their surroundings involves reading text in the image. But today's VQA models can not read! Our paper takes a first step towards addressing this problem. ... More Decoding Molecular Graph Embeddings with Reinforcement LearningApr 18 2019We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but these approaches require sophisticated ... More edGNN: a Simple and Powerful GNN for Directed Labeled GraphsApr 18 2019The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings. Building on previous work, we theoretically show that edGNN, our model for directed labeled ... More Batch Tournament Selection for Genetic ProgrammingApr 18 2019Lexicase selection achieves very good solution quality by introducing ordered test cases. However, the computational complexity of lexicase selection can prohibit its use in many applications. In this paper, we introduce Batch Tournament Selection (BTS), ... More Inpatient2Vec: Medical Representation Learning for InpatientsApr 18 2019Representation learning (RL) plays an important role in extracting proper representations from complex medical data for various analyzing tasks, such as patient grouping, clinical endpoint prediction and medication recommendation. Medical data can be ... More Deep Representation Learning for Social Network AnalysisApr 18 2019Social network analysis is an important problem in data mining. A fundamental step for analyzing social networks is to encode network data into low-dimensional representations, i.e., network embeddings, so that the network topology structure and other ... More Memory-Sample Tradeoffs for Linear Regression with Small ErrorApr 18 2019We consider the problem of performing linear regression over a stream of $d$-dimensional examples, and show that any algorithm that uses a subquadratic amount of memory exhibits a slower rate of convergence than can be achieved without memory constraints. ... More Matrix Completion With Selective SamplingApr 17 2019Matrix completion is a classical problem in data science wherein one attempts to reconstruct a low-rank matrix while only observing some subset of the entries. Previous authors have phrased this problem as a nuclear norm minimization problem. Almost all ... More Do Lateral Views Help Automated Chest X-ray Predictions?Apr 17 2019Most convolutional neural networks in chest radiology use only the frontal posteroanterior (PA) view to make a prediction. However the lateral view is known to help the diagnosis of certain diseases and conditions. The recently released PadChest dataset ... More Robust Exploration with Tight Bayesian Plausibility SetsApr 17 2019Optimism about the poorly understood states and actions is the main driving force of exploration for many provably-efficient reinforcement learning algorithms. We propose optimism in the face of sensible value functions (OFVF)- a novel data-driven Bayesian ... More Off-Policy Policy Gradient with State Distribution CorrectionApr 17 2019We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states ... More Defensive Quantization: When Efficiency Meets RobustnessApr 17 2019Neural network quantization is becoming an industry standard to efficiently deploy deep learning models on hardware platforms, such as CPU, GPU, TPU, and FPGAs. However, we observe that the conventional quantization approaches are vulnerable to adversarial ... More FLARe: Forecasting by Learning Anticipated RepresentationsApr 17 2019Computational models that forecast the progression of Alzheimer's disease at the patient level are extremely useful tools for identifying high risk cohorts for early intervention and treatment planning. The state-of-the-art work in this area proposes ... More Event-based Vision: A SurveyApr 17 2019Event cameras are bio-inspired sensors that work radically different from traditional cameras. Instead of capturing images at a fixed rate, they measure per-pixel brightness changes asynchronously. This results in a stream of events, which encode the ... More Dynamic Evaluation of Transformer Language ModelsApr 17 2019This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation. Transformers use stacked layers of self-attention that allow them to capture long range dependencies in ... More Document Expansion by Query PredictionApr 17 2019One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content. From the perspective of a question answering system, a useful representation of a document ... More Relay: A High-Level IR for Deep LearningApr 17 2019Frameworks for writing, compiling, and optimizing deep learning (DL) models have recently enabled progress in areas like computer vision and natural language processing. Extending these frameworks to accommodate the rapidly diversifying landscape of DL ... More