NeurIPS 2016 accepted papers on Optimization
63 of the 570 papers accepted at NeurIPS 2016 (11.1%) are on Optimization. They fall into 4 topics.
See NeurIPS 2016 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Nonconvex and smooth optimization · 31 papers
- Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences (140 citations)
- Fast Algorithms for Robust PCA via Gradient Descent (134 citations)
- Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization (107 citations)
- Stochastic Online AUC Maximization (99 citations)
- Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds (80 citations)
- Reshaped Wirtinger Flow for Solving Quadratic System of Equations (74 citations)
- A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order (68 citations)
- A Simple Practical Accelerated Method for Finite Sums (57 citations)
- Tight Complexity Bounds for Optimizing Composite Objectives (49 citations)
- Learning Supervised PageRank with Gradient-Based and Gradient-Free Optimization Methods (38 citations)
- NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization (34 citations)
- The non-convex Burer-Monteiro approach works on smooth semidefinite programs (33 citations)
and 19 more in the interactive map.
Optimizers · 25 papers
- Learning to learn by gradient descent by gradient descent (342 citations)
- Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm (307 citations)
- Stochastic Optimization for Large-scale Optimal Transport (147 citations)
- Barzilai-Borwein Step Size for Stochastic Gradient Descent (131 citations)
- The Parallel Knowledge Gradient Method for Batch Bayesian Optimization (121 citations)
- Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent (41 citations)
- Regularized Nonlinear Acceleration (39 citations)
- Coordinate-wise Power Method (32 citations)
- Cyclades: Conflict-free Asynchronous Machine Learning (31 citations)
- Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles (30 citations)
- A Multi-Batch L-BFGS Method for Machine Learning (25 citations)
- Learning a Metric Embedding for Face Recognition using the Multibatch Method (20 citations)
and 13 more in the interactive map.
Implicit bias and generalization · 5 papers
- Global Optimality of Local Search for Low Rank Matrix Recovery (241 citations)
- Matrix Completion has No Spurious Local Minimum (179 citations)
- Deep Learning without Poor Local Minima (22 citations)
- Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods (12 citations)
- Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes
