Stochastic algorithms with geometric step decay converge linearly on sharp functions

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Primal-dual subgradient methods for convex problems
Minimizing finite sums with the stochastic average gradient
Subgradient methods for sharp weakly convex functions
New computational guarantees for solving convex optimization problems with first order methods, via a function growth condition measure
Faster subgradient methods for functions with Hölderian growth
Rapid, robust, and reliable blind deconvolution via nonconvex optimization
Adaptive restart for accelerated gradient schemes
Phase retrieval: stability and recovery guarantees
PhaseLift: Exact and Stable Signal Recovery from Magnitude Measurements via Convex Programming
Calculus Without Derivatives
Blind Deconvolution Using Convex Programming
Identifiable Surfaces in Constrained Optimization
Optimal methods of smooth convex minimization
Acceleration of Stochastic Approximation by Averaging
On convergence rates of subgradient optimization methods
Variational Analysis
RSG: Beating Subgradient Method without Smoothness and Strong Convexity
Stochastic Methods for Composite and Weakly Convex Optimization Problems
PhaseMax: Convex Phase Retrieval via Basis Pursuit
Stochastic Model-Based Minimization of Weakly Convex Functions
Active Sets, Nonsmoothness, and Sensitivity
Prox-regular functions in variational analysis
Solving (most) of a set of quadratic equalities: composite optimization for robust phase retrieval
Phase retrieval via randomized Kaczmarz: theoretical guarantees
Incremental Majorization-Minimization Optimization with Application to Large-Scale Machine Learning
Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms
A Stochastic Approximation Method