Stochastic gradient methods with inexact oracle
arXiv:1411.4218
Abstract
In the article we lead a brief survey of contemporary gradient type methods (with inexact oracle) for stochastic optimization problems.
60 pages, in Russian
References in corpus (9)
- Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting
- A Universal Catalyst for First-Order Optimization
- An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
- Randomized Dual Coordinate Ascent with Arbitrary Sampling
- Learning From An Optimization Viewpoint
- On Accelerated Methods in Optimization
- Stochastic Intermediate Gradient Method for Convex Problems with Inexact Stochastic Oracle
- Decomposition Techniques for Bilinear Saddle Point Problems and Variational Inequalities with Affine Monotone Operators on Domains Given by Linear Minimization Oracles
- Learning Supervised PageRank with Gradient-Free Optimization Methods
Cited by in corpus (4)
- Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping
- Improved Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandit
- Efficient numerical algorithms for regularized regression problem with applications to traffic matrix estimations
- Numerical methods in large-scale optimization: inexact oracle and primal-dual analysis