ICML 2016 accepted papers on Optimization
41 of the 322 papers accepted at ICML 2016 (12.7%) are on Optimization. They fall into 4 topics.
See ICML 2016 in the interactive map
Submitting to ICML? 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 · 19 papers
- Stochastic Variance Reduction for Nonconvex Optimization (226 citations)
- Variance Reduction for Faster Non-Convex Optimization (119 citations)
- Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling (100 citations)
- Variance-Reduced and Projection-Free Stochastic Optimization (74 citations)
- On Graduated Optimization for Stochastic Non-Convex Problems (54 citations)
- SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization (53 citations)
- Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning (33 citations)
- SDCA without Duality, Regularization, and Individual Convexity (32 citations)
- Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives (26 citations)
- A Superlinearly-Convergent Proximal Newton-type Method for the Optimization of Finite Sums (20 citations)
- On the Iteration Complexity of Oblivious First-Order Optimization Algorithms (19 citations)
- Quadratic Optimization with Orthogonality Constraints: Explicit Lojasiewicz Exponent and Linear Convergence of Line-Search Methods (13 citations)
and 7 more in the interactive map.
Optimizers · 18 papers
- Training Neural Networks Without Gradients: A Scalable ADMM Approach (140 citations)
- Hyperparameter optimization with approximate gradient (132 citations)
- Low-rank tensor completion: a Riemannian manifold preconditioning approach (82 citations)
- Noisy Activation Functions (81 citations)
- A Variational Analysis of Stochastic Gradient Algorithms (54 citations)
- Adaptive Sampling for SGD by Exploiting Side Information (43 citations)
- Black-Box Alpha Divergence Minimization (40 citations)
- Stochastic Quasi-Newton Langevin Monte Carlo (32 citations)
- A Kronecker-factored approximate Fisher matrix for convolution layers (31 citations)
- Learning from Multiway Data: Simple and Efficient Tensor Regression (27 citations)
- A Self-Correcting Variable-Metric Algorithm for Stochastic Optimization (26 citations)
- Preconditioning Kernel Matrices (20 citations)
and 6 more in the interactive map.
