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
Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural NetworksApr 22 2019Recently, deep learning has become a de facto standard in machine learning with convolutional neural networks (CNNs) demonstrating spectacular success on a wide variety of tasks. However, CNNs are typically very demanding computationally at inference ... 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
A Unified Framework for Structured Graph Learning via Spectral ConstraintsApr 22 2019Graph learning from data represents a canonical problem that has received substantial attention in the literature. However, insufficient work has been done in incorporating prior structural knowledge onto the learning of underlying graphical models from ... More
On Learning Non-Convergent Short-Run MCMC Toward Energy-Based ModelApr 22 2019This paper studies a curious phenomenon in learning energy-based model (EBM) using MCMC. In each learning iteration, we generate synthesized examples by running a non-convergent, non-mixing, and non-persistent short-run MCMC toward the current model, ... 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
FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofingApr 22 2019Face Anti-spoofing gains increased attentions recently in both academic and industrial fields. With the emergence of various CNN based solutions, the multi-modal(RGB, depth and IR) methods based CNN showed better performance than single modal classifiers. ... More
Provable Bregman-divergence based Methods for Nonconvex and Non-Lipschitz ProblemsApr 22 2019The (global) Lipschitz smoothness condition is crucial in establishing the convergence theory for most optimization methods. Unfortunately, most machine learning and signal processing problems are not Lipschitz smooth. This motivates us to generalize ... More
HCFContext: Smartphone Context Inference via Sequential History-based Collaborative FilteringApr 21 2019Mobile context determination is an important step for many context aware services such as location-based services, enterprise policy enforcement, building or room occupancy detection for power or HVAC operation, etc. Especially in enterprise scenarios ... 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
PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and TextApr 21 2019We consider open-domain queston answering (QA) where answers are drawn from either a corpus, a knowledge base (KB), or a combination of both of these. We focus on a setting in which a corpus is supplemented with a large but incomplete KB, and on questions ... More
GAN-based Generation and Automatic Selection of Explanations for Neural NetworksApr 21 2019One way to interpret trained deep neural networks (DNNs) is by inspecting characteristics that neurons in the model respond to, such as by iteratively optimising the model input (e.g., an image) to maximally activate specific neurons. However, this requires ... More
LIBS2ML: A Library for Scalable Second Order Machine Learning AlgorithmsApr 20 2019LIBS2ML is a library based on scalable second order learning algorithms for solving large-scale problems, i.e., big data problems in machine learning. LIBS2ML has been developed using MEX files, i.e., C++ with MATLAB/Octave interface to take the advantage ... 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
Minimax Optimal Online Stochastic Learning for Sequences of Convex Functions under Sub-Gradient Observation FailuresApr 19 2019We study online convex optimization under stochastic sub-gradient observation faults, where we introduce adaptive algorithms with minimax optimal regret guarantees. We specifically study scenarios where our sub-gradient observations can be noisy or even ... More
Submodular Maximization Beyond Non-negativity: Guarantees, Fast Algorithms, and ApplicationsApr 19 2019It is generally believed that submodular functions -- and the more general class of $\gamma$-weakly submodular functions -- may only be optimized under the non-negativity assumption $f(S) \geq 0$. In this paper, we show that once the function is expressed ... 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
Reliable Multi-label Classification: Prediction with Partial AbstentionApr 19 2019In contrast to conventional (single-label) classification, the setting of multi-label classification (MLC) allows an instance to belong to several classes simultaneously. Thus, instead of selecting a single class label, predictions take the form of a ... More
Uncertainty about Uncertainty: Near-Optimal Adaptive Algorithms for Estimating Binary Mixtures of Unknown CoinsApr 19 2019Given a mixture between two populations of coins, "positive" coins that have (unknown and potentially different) probabilities of heads $\geq\frac{1}{2}+\Delta$ and negative coins with probabilities $\leq\frac{1}{2}-\Delta$, we consider the task of estimating ... More
Risk Convergence of Centered Kernel Ridge Regression with Large Dimensional DataApr 19 2019This paper carries out a large dimensional analysis of a variation of kernel ridge regression that we call \emph{centered kernel ridge regression} (CKRR), also known in the literature as kernel ridge regression with offset. This modified technique is ... 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
Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like processApr 19 2019We consider deep networks, trained via stochastic gradient descent to minimize L2 loss, with the training labels perturbed by independent noise at each iteration. We characterize the behavior of the training dynamics near any parameter vector that achieves ... More
EmbraceNet: A robust deep learning architecture for multimodal classificationApr 19 2019Classification using multimodal data arises in many machine learning applications. It is crucial not only to model cross-modal relationship effectively but also to ensure robustness against loss of part of data or modalities. In this paper, we propose ... More
Emergence of Compositional Language with Deep Generational TransmissionApr 19 2019Consider a collaborative task that requires communication. Two agents are placed in an environment and must create a language from scratch in order to coordinate. Recent work has been interested in what kinds of languages emerge when deep reinforcement ... More
Online Active Learning: Label Complexity vs. Classification ErrorsApr 19 2019We study online active learning for classifying streaming instances. At each time, the decision maker decides whether to query for the label of the current instance and, in the event of no query, self labels the instance. The objective is to minimize ... More
NNVA: Neural Network Assisted Visual Analysis of Yeast Cell Polarization SimulationApr 19 2019Complex computational models are often designed to simulate real-world physical phenomena in many scientific disciplines. However, these simulation models tend to be computationally very expensive and involve a large number of simulation input parameters ... More
ProductNet: a Collection of High-Quality Datasets for Product Representation LearningApr 18 2019ProductNet is a collection of high-quality product datasets for better product understanding. Motivated by ImageNet, ProductNet aims at supporting product representation learning by curating product datasets of high quality with properly chosen taxonomy. ... 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
Making Meaning: Semiotics Within Predictive Knowledge ArchitecturesApr 18 2019Within Reinforcement Learning, there is a fledgling approach to conceptualizing the environment in terms of predictions. Central to this predictive approach is the assertion that it is possible to construct ontologies in terms of predictions about sensation, ... More
Graph Element Networks: adaptive, structured computation and memoryApr 18 2019We explore the use of graph neural networks (GNNs) to model spatial processes in which there is a priori graphical structure. Similar to finite element analysis, we assign nodes of a GNN to spatial locations and use a computational process defined on ... 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
Sequential Decision Making under Uncertainty with Dynamic Resource ConstraintsApr 18 2019This paper studies a class of constrained restless multi-armed bandits. The constraints are in the form of time varying availability of arms. This variation can be either stochastic or semi-deterministic. A fixed number of arms can be chosen to be played ... 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
SpecAugment: A Simple Data Augmentation Method for Automatic Speech RecognitionApr 18 2019We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking ... 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
DScribe: Library of Descriptors for Machine Learning in Materials ScienceApr 18 2019DScribe is a software package for machine learning that provides popular feature transformations ("descriptors") for atomistic materials simulations. DScribe accelerates the application of machine learning for atomistic property prediction by providing ... More
Inspecting and Interacting with Meaningful Music Representations using VAEApr 18 2019Variational Autoencoders(VAEs) have already achieved great results on image generation and recently made promising progress on music generation. However, the generation process is still quite difficult to control in the sense that the learned latent representations ... More
Neural-Attention-Based Deep Learning Architectures for Modeling Traffic Dynamics on Lane GraphsApr 18 2019Deep neural networks can be powerful tools, but require careful application-specific design to ensure that the most informative relationships in the data are learnable. In this paper, we apply deep neural networks to the nonlinear spatiotemporal physics ... More
Deep Residual Auto-Encoders for Expectation Maximization-based Dictionary LearningApr 18 2019Convolutional dictionary learning (CDL) has become a popular method for learning sparse representations from data. State-of-the-art algorithms perform dictionary learning (DL) through an optimization-based alternating-minimization procedure that comprises ... More
Interplanetary Transfers via Deep Representations of the Optimal Policy and/or of the Value FunctionApr 18 2019A number of applications to interplanetary trajectories have been recently proposed based on deep networks. These approaches often rely on the availability of a large number of optimal trajectories to learn from. In this paper we introduce a new method ... More
Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-based UAV RacingApr 18 2019Autonomous UAV racing has recently emerged as an interesting research problem. The dream is to beat humans in this new fast-paced sport. A common approach is to learn an end-to-end policy that directly predicts controls from raw images by imitating an ... More
A Data Driven Approach for Motion Planning of Autonomous Driving Under Complex ScenarioApr 18 2019To guarantee the safe and efficient motion planning of autonomous driving under dynamic traffic environment, the autonomous vehicle should be equipped with not only the optimal but also a long term efficient policy to deal with complex scenarios. The ... More
Evaluating the Underlying Gender Bias in Contextualized Word EmbeddingsApr 18 2019Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized word embeddings have enhanced ... 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
Convolutional neural networks: a magic bullet for gravitational-wave detection?Apr 18 2019In the last few years, machine learning techniques, in particular convolutional neural networks, have been investigated as a method to replace or complement traditional matched filtering techniques that are used to detect the gravitational-wave signature ... 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
Query-Adaptive Hash Code Ranking for Large-Scale Multi-View Visual SearchApr 18 2019Hash based nearest neighbor search has become attractive in many applications. However, the quantization in hashing usually degenerates the discriminative power when using Hamming distance ranking. Besides, for large-scale visual search, existing hashing ... More
Improving Interactive Reinforcement Agent Planning with Human DemonstrationApr 18 2019TAMER has proven to be a powerful interactive reinforcement learning method for allowing ordinary people to teach and personalize autonomous agents' behavior by providing evaluative feedback. However, a TAMER agent planning with UCT---a Monte Carlo Tree ... More
Disentangled Representation Learning with Information Maximizing AutoencoderApr 18 2019Learning disentangled representation from any unlabelled data is a non-trivial problem. In this paper we propose Information Maximising Autoencoder (InfoAE) where the encoder learns powerful disentangled representation through maximizing the mutual information ... More
Explaining Deep Classification of Time-Series Data with Learned PrototypesApr 18 2019The emergence of deep learning networks raises a need for algorithms to explain their decisions so that users and domain experts can be confident using algorithmic recommendations for high-risk decisions. In this paper we leverage the information-rich ... More
Reducing Noise in GAN Training with Variance Reduced ExtragradientApr 18 2019Using large mini-batches when training generative adversarial networks (GANs) has been recently shown to significantly improve the quality of the generated samples. This can be seen as a simple but computationally expensive way of reducing the noise of ... More
One-dimensional Deep Image Prior for Time Series Inverse ProblemsApr 18 2019We extend the Deep Image Prior (DIP) framework to one-dimensional signals. DIP is using a randomly initialized convolutional neural network (CNN) to solve linear inverse problems by optimizing over weights to fit the observed measurements. Our main finding ... More
Road Crack Detection Using Deep Convolutional Neural Network and Adaptive ThresholdingApr 18 2019Crack is one of the most common road distresses which may pose road safety hazards. Generally, crack detection is performed by either certified inspectors or structural engineers. This task is, however, time-consuming, subjective and labor-intensive. ... More
On Low-rank Trace Regression under General Sampling DistributionApr 18 2019A growing number of modern statistical learning problems involve estimating a large number of parameters from a (smaller) number of observations. In a subset of these problems (matrix completion, matrix compressed sensing, and multi-task learning) the ... More
SPONGE: A generalized eigenproblem for clustering signed networksApr 18 2019We introduce a principled and theoretically sound spectral method for $k$-way clustering in signed graphs, where the affinity measure between nodes takes either positive or negative values. Our approach is motivated by social balance theory, where the ... More
Design of Communication Systems using Deep Learning: A Variational Inference PerspectiveApr 18 2019An approach to design end to end communication system using deep learning leveraging the generative modeling capabilities of autoencoders is presented. The system models are designed using Deep Neural Networks (DNNs) and the objective function for optimizing ... 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
Gotta Catch 'Em All: Using Concealed Trapdoors to Detect Adversarial Attacks on Neural NetworksApr 18 2019Deep neural networks are vulnerable to adversarial attacks. Numerous efforts have focused on defenses that either try to patch `holes' in trained models or try to make it difficult or costly to compute adversarial examples exploiting these holes. In our ... More
A New Class of Time Dependent Latent Factor Models with ApplicationsApr 18 2019In many applications, observed data are influenced by some combination of latent causes. For example, suppose sensors are placed inside a building to record responses such as temperature, humidity, power consumption and noise levels. These random, observed ... 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
Ensemble Convolutional Neural Networks for Mode Inference in Smartphone Travel SurveyApr 18 2019We develop ensemble Convolutional Neural Networks (CNNs) to classify the transportation mode of trip data collected as part of a large-scale smartphone travel survey in Montreal, Canada. Our proposed ensemble library is composed of a series of CNN models ... 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
ZK-GanDef: A GAN based Zero Knowledge Adversarial Training Defense for Neural NetworksApr 17 2019Neural Network classifiers have been used successfully in a wide range of applications. However, their underlying assumption of attack free environment has been defied by adversarial examples. Researchers tried to develop defenses; however, existing approaches ... More
DeepNovoV2: Better de novo peptide sequencing with deep learningApr 17 2019We introduce DeepNovoV2, the state-of-the-art neural networks based model for de novo peptide sequencing. Contrary to existing models like DeepNovo or DeepMatch which represents each spectrum as a long sparse vector, in DeepNovoV2, we propose to directly ... More
An Unsupervised Feature Learning Approach to Reduce False Alarm Rate in ICUsApr 17 2019The high rate of false alarms in intensive care units (ICUs) is one of the top challenges of using medical technology in hospitals. These false alarms are often caused by patients' movements, detachment of monitoring sensors, or different sources of noise ... More
Learning Interpretable Disentangled Representations using Adversarial VAEsApr 17 2019Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a more compact ... More
Semantic Adversarial Attacks: Parametric Transformations That Fool Deep ClassifiersApr 17 2019Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the image pixel space. ... More
LCC: Learning to Customize and Combine Neural Networks for Few-Shot LearningApr 17 2019Meta-learning has been shown to be an effective strategy for few-shot learning. The key idea is to leverage a large number of similar few-shot tasks in order to meta-learn how to best initiate a (single) base-learner for novel few-shot tasks. While meta-learning ... More
A Game Theoretical Framework for the Evaluation of Unmanned Aircraft Systems Airspace Integration ConceptsApr 17 2019Predicting the outcomes of integrating Unmanned Aerial Systems (UAS) into the National Aerospace (NAS) is a complex problem which is required to be addressed by simulation studies before allowing the routine access of UAS into the NAS. This thesis focuses ... 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
Stock Forecasting using M-Band Wavelet-Based SVR and RNN-LSTMs ModelsApr 17 2019The task of predicting future stock values has always been one that is heavily desired albeit very difficult. This difficulty arises from stocks with non-stationary behavior, and without any explicit form. Hence, predictions are best made through analysis ... More
Regression and Classification for Direction-of-Arrival Estimation with Convolutional Recurrent Neural NetworksApr 17 2019We present a novel learning-based approach to estimate the direction-of-arrival (DOA) of a sound source using a convolutional recurrent neural network (CRNN) trained via regression on synthetic data and Cartesian labels. We also describe an improved method ... 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
SACOBRA with Online Whitening for Solving Optimization Problems with High ConditioningApr 17 2019Real-world optimization problems often have expensive objective functions in terms of cost and time. It is desirable to find near-optimal solutions with very few function evaluations. Surrogate-assisted optimizers tend to reduce the required number of ... More
Casting Light on Invisible Cities: Computationally Engaging with Literary CriticismApr 17 2019Literary critics often attempt to uncover meaning in a single work of literature through careful reading and analysis. Applying natural language processing methods to aid in such literary analyses remains a challenge in digital humanities. While most ... More
Vid2Game: Controllable Characters Extracted from Real-World VideosApr 17 2019We are given a video of a person performing a certain activity, from which we extract a controllable model. The model generates novel image sequences of that person, according to arbitrary user-defined control signals, typically marking the displacement ... 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
Decoupled Data Based Approach for Learning to Control Nonlinear Dynamical SystemsApr 17 2019This paper addresses the problem of learning the optimal control policy for a nonlinear stochastic dynamical system with continuous state space, continuous action space and unknown dynamics. This class of problems are typically addressed in stochastic ... More
Towards Robust Deep Reinforcement Learning for Traffic Signal Control: Demand Surges, Incidents and Sensor FailuresApr 17 2019Reinforcement learning (RL) constitutes a promising solution for alleviating the problem of traffic congestion. In particular, deep RL algorithms have been shown to produce adaptive traffic signal controllers that outperform conventional systems. However, ... More
MOSNet: Deep Learning based Objective Assessment for Voice ConversionApr 17 2019Existing objective evaluation metrics for voice conversion (VC) are not always correlated well with human perception. Therefore, training VC models with such criteria may not effectively improve naturalness and similarity of converted speech. In this ... More
A large-scale field test on word-image classification in large historical document collections using a traditional and two deep-learning methodsApr 17 2019This technical report describes a practical field test on word-image classification in a very large collection of more than 300 diverse handwritten historical manuscripts, with 1.6 million unique labeled images and more than 11 million images used in ... More
BS-Nets: An End-to-End Framework For Band Selection of Hyperspectral ImageApr 17 2019Hyperspectral image (HSI) consists of hundreds of continuous narrow bands with high spectral correlation, which would lead to the so-called Hughes phenomenon and the high computational cost in processing. Band selection has been proven effective in avoiding ... More