← Keywords

non-convex optimization

546 papers

Explore in graph

Also known as

IRLS

Co-occurring keywords

stochastic gradient descent (1088) stochastic optimization (1060) gradient descent (1143) convergence rate (606) convergence analysis (394) variance reduction (520) nonconvex optimization (316) saddle point (95) matrix factorization (529) online learning (1770)

Papers

Basis Learning as an Algorithmic Primitive COLT 2016
Fast Algorithms for Robust PCA via Gradient Descent NIPS 2016
Global Optimality of Local Search for Low Rank Matrix Recovery NIPS 2016
The non-convex Burer-Monteiro approach works on smooth semidefinite programs NIPS 2016
Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent NIPS 2016
Solving Random Systems of Quadratic Equations via Truncated Generalized Gradient Flow NIPS 2016
Learning Supervised PageRank with Gradient-Based and Gradient-Free Optimization Methods NIPS 2016
Deep Learning without Poor Local Minima NIPS 2016
A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing NIPS 2016
Matrix Completion has No Spurious Local Minimum NIPS 2016
A Pseudo-Bayesian Algorithm for Robust PCA NIPS 2016
Stochastic Structured Prediction under Bandit Feedback NIPS 2016
On Graduated Optimization for Stochastic Non-Convex Problems ICML 2016
Train faster, generalize better: Stability of stochastic gradient descent ICML 2016
Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives ICML 2016
SDCA without Duality, Regularization, and Individual Convexity ICML 2016
Variance Reduction for Faster Non-Convex Optimization ICML 2016
Low-rank Solutions of Linear Matrix Equations via Procrustes Flow ICML 2016
Convergence of Stochastic Gradient Descent for PCA ICML 2016
Training Neural Networks Without Gradients: A Scalable ADMM Approach ICML 2016
On the Quality of the Initial Basin in Overspecified Neural Networks ICML 2016
Alternating Minimization for Regression Problems with Vector-valued Outputs NIPS 2015
Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems NIPS 2015
Equilibrated adaptive learning rates for non-convex optimization NIPS 2015
Simple, Efficient, and Neural Algorithms for Sparse Coding COLT 2015