Stochastic algorithms with geometric step decay converge linearly on sharp functions
From MaRDI portal
Recommendations
- Subgradient methods for sharp weakly convex functions
- Sharp global convergence guarantees for iterative nonconvex optimization with random data
- scientific article; zbMATH DE number 7306906
- Stochastic gradient descent with Polyak's learning rate
- Stochastic subgradient method converges on tame functions
Cites work
- A Stochastic Approximation Method
- Acceleration of Stochastic Approximation by Averaging
- Active Sets, Nonsmoothness, and Sensitivity
- Adaptive restart for accelerated gradient schemes
- Blind Deconvolution Using Convex Programming
- Calculus without derivatives
- Convergence rate of incremental subgradient algorithms
- Dual averaging methods for regularized stochastic learning and online optimization
- Faster subgradient methods for functions with Hölderian growth
- scientific article; zbMATH DE number 3790208 (Why is no real title available?)
- scientific article; zbMATH DE number 1972910 (Why is no real title available?)
- scientific article; zbMATH DE number 3805870 (Why is no real title available?)
- scientific article; zbMATH DE number 3232960 (Why is no real title available?)
- scientific article; zbMATH DE number 3304564 (Why is no real title available?)
- Identifiable Surfaces in Constrained Optimization
- Incremental majorization-minimization optimization with application to large-scale machine learning
- Loss minimization and parameter estimation with heavy tails
- Manifold identification in dual averaging for regularized stochastic online learning
- Minimizing finite sums with the stochastic average gradient
- New computational guarantees for solving convex optimization problems with first order methods, via a function growth condition measure
- On convergence rates of subgradient optimization methods
- Optimal methods of smooth convex minimization
- Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization. II: Shrinking procedures and optimal algorithms
- Phase retrieval via randomized Kaczmarz: theoretical guarantees
- Phase retrieval: stability and recovery guarantees
- Phaselift: exact and stable signal recovery from magnitude measurements via convex programming
- PhaseMax: Convex Phase Retrieval via Basis Pursuit
- Primal-dual subgradient methods for convex problems
- Prox-regular functions in variational analysis
- Rapid, robust, and reliable blind deconvolution via nonconvex optimization
- RSG: Beating Subgradient Method without Smoothness and Strong Convexity
- Solving (most) of a set of quadratic equalities: composite optimization for robust phase retrieval
- Stochastic Methods for Composite and Weakly Convex Optimization Problems
- Stochastic model-based minimization of weakly convex functions
- Subgradient methods for sharp weakly convex functions
- Variational Analysis
Cited in
(4)- Stochastic optimization over proximally smooth sets
- Nonlinear tomographic reconstruction via nonsmooth optimization
- A model-free first-order method for linear quadratic regulator with \(\tilde{O}(1/\varepsilon)\) sampling complexity
- An adaptive parameter-free and projection-free restarting level set method for constrained convex optimization under the error bound condition
This page was built for publication: Stochastic algorithms with geometric step decay converge linearly on sharp functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6608032)
