NeurIPS 2015

410 papers

Top Research Directions

Research directions most represented by NeurIPS 2015 papers.

Learning Densities with Intractable Normalizing Constants 9
Scaling Gaussian Processes Beyond Cubic Complexity 8
Mitigating Gradient Variance in Stochastic Optimization 7
Multi-Agent Learning Under Bandit Feedback 6
Matrix-Free Curvature Estimation for Deep Learning 6
Scaling Bayesian Sampling via Stochastic Gradient MCMC 6
Convergence Guarantees for Inexact Subproblem Optimization 5
Navigating the Inference Efficiency Accuracy Tradeoff 5
Inducing Point Approximations for Scalable Gaussian Processes 5
Overcoming the Cubic Complexity of Kernel Methods 5
Unified Mathematical Frameworks for Optimization Algorithms 4
Signal Recovery Beyond the Gaussian Measurement Assumption 4
Greedy Maximization for Submodular Subset Selection 4
Overcoming Geometric Mismatch in Parameter Space Optimization 4
Non-Conjugate Inference for Gaussian Processes 4

Top Authors

AuthorPapers
Pradeep Kumar Ravikumar7
Lawrence Carin6
Inderjit S Dhillon5
Le Song5
Zoubin Ghahramani5
Han Liu4
Joshua B. Tenenbaum4
Michael Jordan4
Percy Liang4
Prateek Jain4
Prateek Jain4
Ryan P Adams4
Shie Mannor4
Simon Lacoste-Julien4
Yoshua Bengio4
Zhaoran Wang4
Alex Dimakis3
Ambuj Tewari3
Antonio Torralba3
Christopher Re3

Impactful Papers

Papers from NeurIPS 2015 that shaped research clusters.

Foundational

Influential

Papers

Title
Rate-Agnostic (Causal) Structure Learning
Recognizing retinal ganglion cells in the dark
Recovering Communities in the General Stochastic Block Model Without Knowing the Parameters
Rectified Factor Networks
Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Prediction
Reflection, Refraction, and Hamiltonian Monte Carlo
Regressive Virtual Metric Learning
Regret-Based Pruning in Extensive-Form Games
Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring
Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices
Regularization Path of Cross-Validation Error Lower Bounds
Regularized EM Algorithms: A Unified Framework and Statistical Guarantees
Rethinking LDA: Moment Matching for Discrete ICA
Revenue Optimization against Strategic Buyers
Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach
Robust Feature-Sample Linear Discriminant Analysis for Brain Disorders Diagnosis
Robust Gaussian Graphical Modeling with the Trimmed Graphical Lasso
Robust PCA with compressed data
Robust Portfolio Optimization
Robust Regression via Hard Thresholding
Robust Spectral Inference for Joint Stochastic Matrix Factorization
Saliency, Scale and Information: Towards a Unifying Theory
Sample Complexity Bounds for Iterative Stochastic Policy Optimization
Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning
Sample Complexity of Learning Mahalanobis Distance Metrics
Sample Efficient Path Integral Control under Uncertainty
Sampling from Probabilistic Submodular Models
Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models
Scalable Inference for Gaussian Process Models with Black-Box Likelihoods
Scalable Semi-Supervised Aggregation of Classifiers
Scale Up Nonlinear Component Analysis with Doubly Stochastic Gradients
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Secure Multi-party Differential Privacy
Segregated Graphs and Marginals of Chain Graph Models
Semi-Proximal Mirror-Prox for Nonsmooth Composite Minimization
Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding
Semi-Supervised Factored Logistic Regression for High-Dimensional Neuroimaging Data
Semi-supervised Learning with Ladder Networks
Semi-supervised Sequence Learning
SGD Algorithms based on Incomplete U-statistics: Large-Scale Minimization of Empirical Risk
Shepard Convolutional Neural Networks
Skip-Thought Vectors
Smart-Homes for eHealth
Smooth and Strong: MAP Inference with Linear Convergence
Smooth Interactive Submodular Set Cover
Softstar: Heuristic-Guided Probabilistic Inference
Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems
Space-Time Local Embeddings
Sparse and Low-Rank Tensor Decomposition
Sparse Linear Programming via Primal and Dual Augmented Coordinate Descent

« prev Page 7/9 next »