NIPS2017 papers which have [easy-to-find] arXiv preprints

Deep Subspace Clustering Network, http://arxiv.org/abs/1709.02508v1
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization, http://arxiv.org/abs/1707.06468v2
Probabilistic Models for Integration Error in the Assessment of Functional Cardiac Models, http://arxiv.org/abs/1606.06841v4
Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning, http://arxiv.org/abs/1704.02882v2
Parametric Simplex Method for Sparse Learning, http://arxiv.org/abs/1704.01079v1
Group Sparse Additive Machine, http://arxiv.org/abs/1206.4673v1
The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings, http://arxiv.org/abs/1703.00864v2
Inferring Generative Model Structure with Static Analysis, http://arxiv.org/abs/1709.02477v1
On Structured Prediction Theory with Calibrated Convex Surrogate Losses, http://arxiv.org/abs/1703.02403v2
Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model, http://arxiv.org/abs/1706.01554v1
Universal Style Transfer via Feature Transforms, http://arxiv.org/abs/1705.08086v1
Pose Guided Person Image Generation, http://arxiv.org/abs/1705.09368v4
On the Power of Truncated SVD for General High-rank Matrix Estimation Problems, http://arxiv.org/abs/1702.06861v1
f-GANs in an Information Geometric Nutshell, http://arxiv.org/abs/1707.04385v1
Learning multiple visual domains with residual adapters, http://arxiv.org/abs/1705.08045v4
Dykstra's Algorithm, ADMM, and Coordinate Descent: Connections, Insights, and Extensions, http://arxiv.org/abs/1705.04768v1
Hypothesis Transfer Learning via Transformation Functions, http://arxiv.org/abs/1612.01020v3
Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization, http://arxiv.org/abs/1703.00439v3
Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks, http://arxiv.org/abs/1703.04379v3
Efficient Online Linear Optimization with Approximation Algorithms, http://arxiv.org/abs/1709.03093v1
Geometric Descent Method for Convex Composite Minimization, http://arxiv.org/abs/1612.09034v4
Nonparametric Online Regression while Learning the Metric, http://arxiv.org/abs/1705.07853v1
Safe and Nested Subgame Solving for Imperfect-Information Games, http://arxiv.org/abs/1705.02955v2
Unsupervised Image-to-Image Translation Networks, http://arxiv.org/abs/1703.00848v1
Improved Dynamic Regret for Non-degeneracy Functions, http://arxiv.org/abs/1608.03933v1
Deep Mean-Shift Priors for Image Restoration, http://arxiv.org/abs/1709.03749v1
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees, http://arxiv.org/abs/1705.11041v2
Label Distribution Learning Forests, http://arxiv.org/abs/1702.06086v2
Unsupervised object learning from dense equivariant image labelling, http://arxiv.org/abs/1706.02932v1
Safe Model-based Reinforcement Learning with Stability Guarantees, http://arxiv.org/abs/1705.08551v1
Online multiclass boosting, http://arxiv.org/abs/1702.07305v2
GP CaKe: Effective brain connectivity with causal kernels, http://arxiv.org/abs/1705.05603v1
Decoupling "when to update" from "how to update", http://arxiv.org/abs/1706.02613v1
Learning to Pivot with Adversarial Networks, http://arxiv.org/abs/1611.01046v3
Active Bias: Training a More Accurate Neural Network by Emphasizing High Variance Samples, http://arxiv.org/abs/1704.07433v2
Inductive Representation Learning on Large Graphs, http://arxiv.org/abs/1706.02216v1
Gradient Descent Can Take Exponential Time to Escape Saddle Points, http://arxiv.org/abs/1705.10412v1
Union of Intersections (UoI) for Interpretable Data Driven Discovery and Prediction, http://arxiv.org/abs/1705.07585v1
Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding, http://arxiv.org/abs/1705.08006v2
Integration Methods and Optimization Algorithms, http://arxiv.org/abs/1702.06751v1
Sharpness, Restart and Acceleration, http://arxiv.org/abs/1702.03828v1
Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations, http://arxiv.org/abs/1704.00648v2
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results, http://arxiv.org/abs/1703.01780v2
Matching neural paths: transfer from recognition to correspondence search, http://arxiv.org/abs/1705.08272v2
Linearly constrained Gaussian processes, http://arxiv.org/abs/1703.00787v1
Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets, http://arxiv.org/abs/1705.10479v1
Online Prediction with Selfish Experts, http://arxiv.org/abs/1702.03615v2
Learning Unknown Markov Decision Processes: A Thompson Sampling Approach, http://arxiv.org/abs/1709.04570v1
Testing and Learning on Distributions with Symmetric Noise Invariance, http://arxiv.org/abs/1703.07596v1
A Dirichlet Mixture Model of Hawkes Processes for Event Sequence Clustering, http://arxiv.org/abs/1701.09177v4
Accelerated consensus via Min-Sum Splitting, http://arxiv.org/abs/1706.03807v1
Nonbacktracking Bounds on the Influence in Independent Cascade Models, http://arxiv.org/abs/1706.05295v2
Learning with Feature Evolvable Streams, http://arxiv.org/abs/1706.05259v1
Linear regression without correspondence, http://arxiv.org/abs/1705.07048v1
Probabilistic Rule Realization and Selection, http://arxiv.org/abs/1709.01674v1
Nearest-Neighbor Sample Compression: Efficiency, Consistency, Infinite Dimensions, http://arxiv.org/abs/1705.08184v1
A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis, http://arxiv.org/abs/1703.08937v1
Learning Multiple Tasks with Deep Relationship Networks, http://arxiv.org/abs/1506.02117v3
Online to Offline Conversions and Adaptive Minibatch Sizes, http://arxiv.org/abs/1705.10499v2
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure, http://arxiv.org/abs/1610.00970v5
Deep Learning with Topological Signatures, http://arxiv.org/abs/1707.04041v1
Submultiplicative Glivenko-Cantelli and Uniform Convergence of Revenues, http://arxiv.org/abs/1705.08430v2
What-If Reasoning using Counterfactual Gaussian Processes, http://arxiv.org/abs/1703.10651v2
Train longer, generalize better: closing the generalization gap in large batch training of neural networks, http://arxiv.org/abs/1705.08741v1
Adaptive Clustering through Semidefinite Programming, http://arxiv.org/abs/1705.06615v1
The Numerics of GANs, http://arxiv.org/abs/1705.10461v1
Practical Bayesian Optimization for Model Fitting with Bayesian Adaptive Direct Search, http://arxiv.org/abs/1705.04405v1
Revenue Optimization with Approximate Bid Predictions, http://arxiv.org/abs/1706.04732v1
Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization, http://arxiv.org/abs/1702.08651v1
Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models, http://arxiv.org/abs/1702.03275v2
Generating steganographic images via adversarial training, http://arxiv.org/abs/1703.00371v3
Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration, http://arxiv.org/abs/1705.09634v1
PixelGAN Autoencoders, http://arxiv.org/abs/1706.00531v1
Consistent Multitask Learning with Nonlinear Output Relations, http://arxiv.org/abs/1705.08118v2
Stabilizing Training of Generative Adversarial Networks through Regularization, http://arxiv.org/abs/1705.09367v1
First-Order Adaptive Sample Size Methods to Reduce Complexity of Empirical Risk Minimization, http://arxiv.org/abs/1709.00599v1
Bayesian Dyadic Trees and Histograms for Regression, http://arxiv.org/abs/1708.00078v1
Elementary Symmetric Polynomials for Optimal Experimental Design, http://arxiv.org/abs/1705.09677v1
Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols, http://arxiv.org/abs/1705.11192v1
Backprop without Learning Rates Through Coin Betting, http://arxiv.org/abs/1705.07795v2
Pixels to Graphs by Associative Embedding, http://arxiv.org/abs/1706.07365v1
MMD GAN: Towards Deeper Understanding of Moment Matching Network, http://arxiv.org/abs/1705.08584v1
The Reversible Residual Network: Backpropagation Without Storing Activations, http://arxiv.org/abs/1707.04585v1
Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe, http://arxiv.org/abs/1702.06917v2
Expectation Propagation for t-Exponential Family Using Q-Algebra, http://arxiv.org/abs/1705.09046v2
Few-Shot Learning Through an Information Retrieval Lens, http://arxiv.org/abs/1707.02610v1
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation, http://arxiv.org/abs/1705.08475v1
Associative Embedding: End-to-End Learning for Joint Detection and Grouping, http://arxiv.org/abs/1611.05424v2
Practical Locally Private Heavy Hitters, http://arxiv.org/abs/1707.04982v1
Differentiable Learning of Logical Rules for Knowledge Base Reasoning, http://arxiv.org/abs/1702.08367v2
Masked Autoregressive Flow for Density Estimation, http://arxiv.org/abs/1705.07057v1
Non-convex Finite-Sum Optimization Via SCSG Methods, http://arxiv.org/abs/1706.09156v1
Fast Black-box Variational Inference through Stochastic Trust-Region Optimization, http://arxiv.org/abs/1706.02375v1
SGD Learns the Conjugate Kernel Class of the Network, http://arxiv.org/abs/1702.08503v2
Noise-Tolerant Interactive Learning Using Pairwise Comparisons, http://arxiv.org/abs/1704.05820v2
Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems, http://arxiv.org/abs/1709.04482v1
Information Theoretic Properties of Markov Random Fields, and their Algorithmic Applications, http://arxiv.org/abs/1705.11107v1
Fisher GAN, http://arxiv.org/abs/1705.09675v2
Information-theoretic analysis of generalization capability of learning algorithms, http://arxiv.org/abs/1705.07809v1
Rigorous Dynamics and Consistent Estimation in Arbitrarily Conditioned Linear Systems , http://arxiv.org/abs/1706.06054v1
Accuracy First: Selecting a Differential Privacy Level for Accuracy Constrained ERM, http://arxiv.org/abs/1705.10829v1
Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network, http://arxiv.org/abs/1709.04555v1
Parallel Streaming Wasserstein Barycenters, http://arxiv.org/abs/1705.07443v1
Dual Discriminator Generative Adversarial Nets, http://arxiv.org/abs/1709.03831v1
On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning, http://arxiv.org/abs/1706.06066v1
Bridging the Gap Between Value and Policy Based Reinforcement Learning, http://arxiv.org/abs/1702.08892v2
Alternating Estimation for Structured High-Dimensional Multi-Response Models, http://arxiv.org/abs/1606.08957v1
Decomposable Submodular Function Minimization: Discrete and Continuous, http://arxiv.org/abs/1703.01830v1
Gauging Variational Inference, http://arxiv.org/abs/1703.01056v5
Beyond Parity: Fairness Objectives for Collaborative Filtering, http://arxiv.org/abs/1705.08804v1
Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach, http://arxiv.org/abs/1707.06334v2
Deep Voice 2: Multi-Speaker Neural Text-to-Speech, http://arxiv.org/abs/1705.08947v1
Continual Learning with Deep Generative Replay, http://arxiv.org/abs/1705.08690v2
Learning Causal Structures Using Regression Invariance, http://arxiv.org/abs/1705.09644v1
Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback, http://arxiv.org/abs/1605.06593v2
Reinforcement Learning under Model Mismatch, http://arxiv.org/abs/1706.04711v1
Hierarchical Attentive Recurrent Tracking, http://arxiv.org/abs/1706.09262v2
Rotting Bandits, http://arxiv.org/abs/1702.07274v3
Unbiased estimates for linear regression via volume sampling, http://arxiv.org/abs/1705.06908v3
Stein Variational Gradient Descent as Gradient Flow, http://arxiv.org/abs/1704.07520v1
Shallow Updates for Deep Reinforcement Learning, http://arxiv.org/abs/1705.07461v1
Adversarial Ranking for Language Generation, http://arxiv.org/abs/1705.11001v1
Generalization Properties of Learning with Random Features, http://arxiv.org/abs/1602.04474v3
Differentially private Bayesian learning on distributed data, http://arxiv.org/abs/1703.01106v2
Learning to Compose Domain-Specific Transformations for Data Augmentation, http://arxiv.org/abs/1709.01643v1
Wasserstein Learning of Deep Generative Point Process Models, http://arxiv.org/abs/1705.08051v1
Streaming Sparse Gaussian Process Approximations, http://arxiv.org/abs/1705.07131v1
A Regularized Framework for Sparse and Structured Neural Attention, http://arxiv.org/abs/1705.07704v1
Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes, http://arxiv.org/abs/1704.02801v2
Certified Defenses for Data Poisoning Attacks, http://arxiv.org/abs/1706.03691v1
Limitations on Variance-Reduction and Acceleration Schemes for Finite Sums Optimization, http://arxiv.org/abs/1706.01686v1
Unsupervised Sequence Classification using Sequential Output Statistics, http://arxiv.org/abs/1702.07817v2
Concrete Dropout, http://arxiv.org/abs/1705.07832v1
A multi-agent reinforcement learning model of common-pool resource appropriation, http://arxiv.org/abs/1707.06600v2
Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks, http://arxiv.org/abs/1704.06803v1
Reducing Reparameterization Gradient Variance, http://arxiv.org/abs/1705.07880v1
Joint distribution optimal transportation for domain adaptation, http://arxiv.org/abs/1705.08848v1
Multiresolution Kernel Approximation for Gaussian Process Regression, http://arxiv.org/abs/1708.02183v1
Diving into the shallows: a computational perspective on large-scale shallow learning, http://arxiv.org/abs/1703.10622v2
Inferring The Latent Structure of Human Decision-Making from Raw Visual Inputs, http://arxiv.org/abs/1703.08840v1
Recursive Sampling for the Nystrom Method, http://arxiv.org/abs/1605.07583v4
Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning, http://arxiv.org/abs/1706.00387v1
Conservative Contextual Linear Bandits, http://arxiv.org/abs/1611.06426v2
On-the-fly Operation Batching in Dynamic Computation Graphs, http://arxiv.org/abs/1705.07860v1
Nonlinear Acceleration of Stochastic Algorithms, http://arxiv.org/abs/1706.07270v2
Streaming Weak Submodularity: Interpreting Neural Networks on the Fly, http://arxiv.org/abs/1703.02647v2
Counterfactual Fairness, http://arxiv.org/abs/1703.06856v2
Triple Generative Adversarial Nets, http://arxiv.org/abs/1703.02291v3
The Marginal Value of Adaptive Gradient Methods in Machine Learning, http://arxiv.org/abs/1705.08292v1
Aggressive Sampling for Multi-class to Binary Reduction with Applications to Text Classification, http://arxiv.org/abs/1701.06511v3
Deconvolutional Paragraph Representation Learning, http://arxiv.org/abs/1708.04729v2
Efficient Use of Limited-Memory Resources to Accelerate Linear Learning, http://arxiv.org/abs/1708.05357v1
Sobolev Training for Neural Networks, http://arxiv.org/abs/1706.04859v3
Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach, http://arxiv.org/abs/1705.07086v1
Polynomial Codes: an Optimal Design for High-Dimensional Coded Matrix Multiplication, http://arxiv.org/abs/1705.10464v1
Unsupervised Learning of Disentangled Representations from Video, http://arxiv.org/abs/1705.10915v1
Improved Graph Laplacian via Geometric Self-Consistency, http://arxiv.org/abs/1406.0118v1
Online Learning of Optimal Bidding Strategy in Repeated Multi-Commodity Auctions, http://arxiv.org/abs/1703.02567v4
Trimmed Density Ratio Estimation, http://arxiv.org/abs/1703.03216v2
Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems, http://arxiv.org/abs/1609.09059v2
Doubly Stochastic Variational Inference for Deep Gaussian Processes, http://arxiv.org/abs/1705.08933v1
Overcoming Catastrophic Forgetting by Incremental Moment Matching, http://arxiv.org/abs/1703.08475v2
Balancing information exposure in social networks, http://arxiv.org/abs/1709.01491v1
Query Complexity of Clustering with Side Information, http://arxiv.org/abs/1706.07719v1
Robust Optimization for Non-Convex Objectives, http://arxiv.org/abs/1707.01047v1
Adaptive Classification for Prediction Under a Budget, http://arxiv.org/abs/1705.10194v1
Beyond Worst-case: A Probabilistic Analysis of Affine Policies in Dynamic Optimization , http://arxiv.org/abs/1706.05737v1
A unified approach to interpreting model predictions, http://arxiv.org/abs/1705.07874v1
Stochastic Approximation for Canonical Correlation Analysis, http://arxiv.org/abs/1702.06818v1
Scalable Variational Inference for Dynamical Systems, http://arxiv.org/abs/1705.07079v1
Working hard to know your neighbor's margins: Local descriptor learning loss, http://arxiv.org/abs/1705.10872v2
Accelerated Stochastic Greedy Coordinate Descent by Soft Thresholding Projection onto Simplex, http://arxiv.org/abs/1702.07842v2
Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon, http://arxiv.org/abs/1705.07565v1
Monte-Carlo Tree Search by Best Arm Identification, http://arxiv.org/abs/1706.02986v1
Hash Embeddings for Efficient Word Representations, http://arxiv.org/abs/1709.03933v1
A simple neural network module for relational reasoning, http://arxiv.org/abs/1706.01427v1
Active Exploration for Learning Symbolic Representations, http://arxiv.org/abs/1709.01490v1
Polynomial time algorithms for dual volume sampling, http://arxiv.org/abs/1703.02674v2
Hindsight Experience Replay, http://arxiv.org/abs/1707.01495v2
Teaching Machines to Describe Images with Natural Language Feedback, http://arxiv.org/abs/1706.00130v2
Efficient Modeling of Latent Information in Supervised Learning using Gaussian Processes, http://arxiv.org/abs/1705.09862v1
K-Medoids For K-Means Seeding, http://arxiv.org/abs/1609.04723v4
Robust Imitation of Diverse Behaviors, http://arxiv.org/abs/1707.02747v2
Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent, http://arxiv.org/abs/1705.09056v5
A Sample Complexity Measure with Applications to Learning Optimal Auctions, http://arxiv.org/abs/1704.02598v2
Thinking Fast and Slow with Deep Learning and Tree Search, http://arxiv.org/abs/1705.08439v1
Hybrid Reward Architecture for Reinforcement Learning, http://arxiv.org/abs/1706.04208v1
A Greedy Approach for Budgeted Maximum Inner Product Search, http://arxiv.org/abs/1610.03317v1
Towards Understanding Adversarial Learning for Joint Distribution Matching, http://arxiv.org/abs/1709.01215v1
Improved Semi-supervised Learning with GANs using Manifold Invariances, http://arxiv.org/abs/1705.08850v1
Approximation and Convergence Properties of Generative Adversarial Learning, http://arxiv.org/abs/1705.08991v1
From Bayesian Sparsity to Gated Recurrent Nets, http://arxiv.org/abs/1706.02815v2
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?, http://arxiv.org/abs/1703.04977v1
Gradient descent GAN optimization is locally stable, http://arxiv.org/abs/1706.04156v1
Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks, http://arxiv.org/abs/1706.00038v1
Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model, http://arxiv.org/abs/1706.03458v1
Do Deep Neural Networks Suffer from Crowding?, http://arxiv.org/abs/1706.08616v1
Learning from Complementary Labels, http://arxiv.org/abs/1705.07541v1
Clustering with Noisy Queries, http://arxiv.org/abs/1706.07510v1
Training Quantized Nets: A Deeper Understanding, http://arxiv.org/abs/1706.02379v2
Permutation-based Causal Inference Algorithms with Interventions, http://arxiv.org/abs/1705.10220v1
Gradient Methods for Submodular Maximization, http://arxiv.org/abs/1708.03949v2
Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos, http://arxiv.org/abs/1703.01138v1
Collaborative Deep Learning in Fixed Topology Networks, http://arxiv.org/abs/1706.07880v1
Learning Disentangled Representations with Semi-Supervised Deep Generative Models, http://arxiv.org/abs/1706.00400v1
A framework for Multi-A(rmed)/B(andit) Testing with Online FDR Control, http://arxiv.org/abs/1706.05378v1
Early stopping for kernel boosting algorithms: A general analysis with localized complexities, http://arxiv.org/abs/1707.01543v1
Gaussian Quadrature for Kernel Features, http://arxiv.org/abs/1709.02605v1
Value Prediction Network, http://arxiv.org/abs/1707.03497v1
Implicit Regularization in Matrix Factorization, http://arxiv.org/abs/1705.09280v1
Asynchronous Coordinate Descent under More Realistic Assumptions, http://arxiv.org/abs/1705.08494v2
Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls, http://arxiv.org/abs/1708.02105v1
Invariance and Stability of Deep Convolutional Representations, http://arxiv.org/abs/1706.03078v1
Statistical Cost Sharing, http://arxiv.org/abs/1703.03111v1
The Expressive Power of Neural Networks: A View from the Width, http://arxiv.org/abs/1709.02540v1
Spectrally-normalized margin bounds for neural networks, http://arxiv.org/abs/1706.08498v1
Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes, http://arxiv.org/abs/1706.06544v1
Scalable Planning with Tensorflow for Hybrid Nonlinear Domains, http://arxiv.org/abs/1704.07511v2
Boltzmann Exploration Done Right, http://arxiv.org/abs/1705.10257v1
Poincaré Embeddings for Learning Hierarchical Representations, http://arxiv.org/abs/1705.08039v2
Learning Combinatorial Optimization Algorithms over Graphs, http://arxiv.org/abs/1704.01665v3
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles, http://arxiv.org/abs/1612.01474v2
Causal Effect Inference with Deep Latent Variable Models, http://arxiv.org/abs/1705.08821v1
Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity, http://arxiv.org/abs/1703.01196v1
Gradient Episodic Memory for Continuum Learning, http://arxiv.org/abs/1706.08840v4
Good Semi-supervised Learning That Requires a Bad GAN, http://arxiv.org/abs/1705.09783v2
Towards Generalization and Simplicity in Continuous Control, http://arxiv.org/abs/1703.02660v1
Modulating early visual processing by language, http://arxiv.org/abs/1707.00683v1
Learning Mixture of Gaussians with Streaming Data, http://arxiv.org/abs/1707.02391v1
Approximation Algorithms for $\ell_0$-Low Rank Approximation, http://arxiv.org/abs/1705.06730v1
Structured Bayesian Pruning via Log-Normal Multiplicative Noise, http://arxiv.org/abs/1705.07283v1
Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin, http://arxiv.org/abs/1708.00339v2
Acceleration and Averaging in Stochastic Descent Dynamics, http://arxiv.org/abs/1707.06219v1
Kernel functions based on triplet comparisons, http://arxiv.org/abs/1607.08456v1
An Error Detection and Correction Framework for Connectomics, http://arxiv.org/abs/1708.02599v1
Style Transfer from Non-parallel Text by Cross-Alignment, http://arxiv.org/abs/1705.09655v1
Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference, http://arxiv.org/abs/1703.09194v3
Kernel Feature Selection via Conditional Covariance Minimization, http://arxiv.org/abs/1707.01164v1
Statistical Convergence Analysis of Gradient EM on General Gaussian Mixture Models, http://arxiv.org/abs/1705.08530v1
Real Time Image Saliency for Black Box Classifiers, http://arxiv.org/abs/1705.07857v1
Stochastic Mirror Descent for Non-Convex Optimization, http://arxiv.org/abs/1705.02031v1

arturbekasov/nips2017-arxiv-papers.md