ICML2017_arXiv
ICML 2017 accepted papers on arXiv.org
Accepted Paperlist: https://2017.icml.cc/Conferences/2017/AcceptedPapersInitial
Papers and links:
Priv’IT: Private and Sample Efficient Identity Testing
Being Robust (in High-Dimensions) Can Be Practical
Unifying task specification in reinforcement learning
Learning the Structure of Generative Models without Labeled Data
Deep Tensor Convolution on Multicores
Beyond Filters: Compact Feature Map for Portable Deep Model
Fast k-Nearest Neighbour Search via Prioritized DCI
An Adaptive Test of Independence with Analytic Kernel Embeddings
Deep Transfer Learning with Joint Adaptation Networks
Robust Probabilistic Modeling with Bayesian Data Reweighting
Distributed and Provably Good Seedings for k-Means in Constant Rounds
Analysis and Optimization of Graph Decompositions by Lifted Multicuts
Curiosity-driven Exploration by Self-supervised Prediction
Consistent On-Line Off-Policy Evaluation
Oracle Complexity of Second-Order Methods for Finite-Sum Problems
Active Learning for Accurate Estimation of Linear Models
Multiple Clustering Views from Multiple Uncertain Experts
Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition
Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging
How close are the eigenvectors and eigenvalues of the sample and actual covariance matrices?
Follow the Compressed Leader: Even Faster Online Learning of Eigenvectors
Faster Principal Component Regression via Optimal Polynomial Approximation to Matrix sgn(x)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
Dynamic Word Embeddings via Skip-Gram Filtering
Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use
Breaking Locality Accelerates Block Gauss-Seidel
Scalable Multi-Class Gaussian Process Classification using Expectation Propagation
Canopy --- Fast Sampling with Cover Trees
Lazifying Conditional Gradient Algorithms
Conditional Accelerated Lazy Stochastic Gradient Descent
A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates
A Semismooth Newton Method for Fast, Generic Convex Programming
Evaluating Bayesian Models with Posterior Dispersion Indices
Kernelized Tensor Factorization Machines with Applications to Neuroimaging
ChoiceRank: Identifying Preferences from Node Traffic in Networks
Guarantees for Greedy Maximization of Non-submodular Functions with Applications
Uniform Deviation Bounds for Unbounded Loss Functions like k-Means
Sliced Wasserstein Kernel for Persistence Diagrams
Measuring Sample Quality with Kernels
Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery
Neural Message Passing for Quantum Chemistry
Online Learning with Local Permutations and Delayed Feedback
Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs
Delta Networks for Optimized Recurrent Network Computation
Analytical Guarantees on Numerical Precision of Deep Neural Networks
Latent Intention Dialogue Models
Cost-Optimal Learning of Causal Graphs
Local Bayesian Optimization of Motor Skills
A Unified View of Multi-Label Performance Measures
Robust Adversarial Reinforcement Learning
Learning Infinite Layer Networks without the Kernel Trick
Differentially Private Clustering in High-Dimensional Euclidean Spaces
Regularising Non-linear Models Using Feature Side-information
Intelligible Language Modeling with Input Switched Affine Networks
Efficient softmax approximation for GPUs
Soft-DTW: a Differentiable Loss Function for Time-Series
Tensor-Train Recurrent Neural Networks for Video Classification
Minimax Regret Bounds for Reinforcement LEarning
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
Learned Optimizers that Scale and Generalize
Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation
Multilevel Clustering via Wasserstein Means
Estimating individual treatment effect: generalization bounds and algorithms
Online Multiview Learning: Dropping Convexity for Better Efficiency