Algorithms with gradient clipping for stochastic optimization with heavy-tailed noise
From MaRDI portal
Recommendations
- High-probability complexity bounds for non-smooth stochastic convex optimization with heavy-tailed noise
- Efficient learning with robust gradient descent
- Nonlinear Gradient Mappings and Stochastic Optimization: A General Framework with Applications to Heavy-Tail Noise
- Gradient-free methods for non-smooth convex stochastic optimization with heavy-tailed noise on convex compact
- Randomized smoothing for stochastic optimization
Cites work
- Algorithms of robust stochastic optimization based on mirror descent method
- Finite-dimensional variational inequality and nonlinear complementarity problems: A survey of theory, algorithms and applications
- First-order methods of smooth convex optimization with inexact oracle
- Large-scale convex optimization. Algorithms \& analyses via monotone operators
- On Bernstein-type inequalities for martingales.
- On tail probabilities for martingales
- Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
- Probability Inequalities for the Sum of Independent Random Variables
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
- Stochastic model-based minimization of weakly convex functions
- Universal method for stochastic composite optimization problems
This page was built for publication: Algorithms with gradient clipping for stochastic optimization with heavy-tailed noise
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6204268)
