A fast non-monotone line search for stochastic gradient descent
From MaRDI portal
Publication:6572737
Recommendations
- Convergence rates for the stochastic gradient descent method for non-convex objective functions
- Stochastic momentum methods for non-convex learning without bounded assumptions
- Stochastic gradient descent with Polyak's learning rate
- A stochastic line search method with expected complexity analysis
- Probabilistic line searches for stochastic optimization
Cites work
- A Nonmonotone Line Search Technique for Newton’s Method
- A nonmonotone trust-region line search method for large-scale unconstrained optimization
- A Stochastic Approximation Method
- Adaptive subgradient methods for online learning and stochastic optimization
- An inexact line search approach using modified nonmonotone strategy for unconstrained optimization
- Numerical Optimization
- Robust Stochastic Approximation Approach to Stochastic Programming
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
- Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm
- The watchdog technique for forcing convergence in algorithms for constrained optimization
Cited in
(2)
This page was built for publication: A fast non-monotone line search for stochastic gradient descent
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6572737)
