NeurIPS 2017

718 papers

Top Research Directions

Research directions most represented by NeurIPS 2017 papers.

Scaling Gaussian Processes Beyond Cubic Complexity 12
Mitigating Mode Collapse and Instability in Generative Training 8
Parameter Agnostic Optimization for Unknown Problem Constants 7
The Pareto Frontier of Algorithmic Accuracy and Fairness 7
Kernel Hyperparameter Sensitivity in Distributional Metrics 7
Overcoming the Cubic Complexity of Kernel Methods 7
Enforcing Bidirectional Consistency in Latent Spaces 6
Multi-Agent Learning Under Bandit Feedback 6
Mitigating Posterior Collapse in Latent Variable Models 6
Overcoming the Convexity Constraint in Modern Optimization 6
Basins of Attraction in Nonconvex Optimization 6
Mitigating the Curse of Dimensionality in Density Estimation 6
The Expressivity Bottleneck of Invertible Neural Networks 5
Non-linear Modeling of Neural Population Dynamics 5
Beyond the Linear Assumption in Reward Modeling 5

Top Authors

AuthorPapers
Lawrence Carin9
Alex Schwing6
Andreas Krause5
Le Song5
Michael Jordan5
Nicolas Heess5
Pieter Abbeel5
Razvan Pascanu5
Aarti Singh4
Andrew Gordon Wilson4
Barnabas Poczos4
Chunyuan Li4
David Blei4
David Silver4
David Woodruff4
Jiajun Wu4
Jiashi Feng4
Joshua B. Tenenbaum4
Masashi Sugiyama4
Nathan Srebro4

Impactful Papers

Papers from NeurIPS 2017 that shaped research clusters.

Foundational

Influential

Papers

Title
Recycling Privileged Learning and Distribution Matching for Fairness
Reducing Reparameterization Gradient Variance
Regret Analysis for Continuous Dueling Bandit
Regret Minimization in MDPs with Options without Prior Knowledge
Regularized Modal Regression with Applications in Cognitive Impairment Prediction
Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
Reinforcement Learning under Model Mismatch
Reliable Decision Support using Counterfactual Models
Renyi Differential Privacy Mechanisms for Posterior Sampling
Repeated Inverse Reinforcement Learning
Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice
Revenue Optimization with Approximate Bid Predictions
Revisit Fuzzy Neural Network: Demystifying Batch Normalization and ReLU with Generalized Hamming Network
Revisiting Perceptron: Efficient and Label-Optimal Learning of Halfspaces
Riemannian approach to batch normalization
Rigorous Dynamics and Consistent Estimation in Arbitrarily Conditioned Linear Systems
Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes
Robust Conditional Probabilities
Robust Estimation of Neural Signals in Calcium Imaging
Robust Hypothesis Test for Nonlinear Effect with Gaussian Processes
Robust Imitation of Diverse Behaviors
Robust Optimization for Non-Convex Objectives
Rotting Bandits
Runtime Neural Pruning
Safe Adaptive Importance Sampling
Safe and Nested Subgame Solving for Imperfect-Information Games
Safe Model-based Reinforcement Learning with Stability Guarantees
SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud
Saliency-based Sequential Image Attention with Multiset Prediction
Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions
Scalable Demand-Aware Recommendation
Scalable Generalized Linear Bandits: Online Computation and Hashing
Scalable Levy Process Priors for Spectral Kernel Learning
Scalable Model Selection for Belief Networks
Scalable Planning with Tensorflow for Hybrid Nonlinear Domains
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
Scalable Variational Inference for Dynamical Systems
SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
Second-order Optimization for Deep Reinforcement Learning using Kronecker-factored Approximation
Selective Classification for Deep Neural Networks
Self-Normalizing Neural Networks
Self-Supervised Intrinsic Image Decomposition
Self-supervised Learning of Motion Capture
Semisupervised Clustering, AND-Queries and Locally Encodable Source Coding
Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks
Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
SGD Learns the Conjugate Kernel Class of the Network
Shallow Updates for Deep Reinforcement Learning
Shape and Material from Sound
Sharpness, Restart and Acceleration

« prev Page 12/15 next »