Ritz-like values in steplength selections for stochastic gradient methods
From MaRDI portal
Recommendations
- On the steplength selection in stochastic gradient methods
- On the steplength selection in gradient methods for unconstrained optimization
- On the Barzilai and Borwein choice of steplength for the gradient method
- On the linear convergence of the stochastic gradient method with constant step-size
- A generalization of s-step variants of gradient methods
- On stochastic gradient and subgradient methods with adaptive steplength sequences
- New adaptive stepsize selections in gradient methods
- Publication:3200898
- scientific article; zbMATH DE number 3922382
- Step-sizes for the gradient method
Cites work
- A limited memory steepest descent method
- Adaptive Regularization Algorithms with Inexact Evaluations for Nonconvex Optimization
- Adaptive sampling strategies for stochastic optimization
- Alternate minimization gradient method
- An introduction to matrix concentration inequalities
- Gradient methods with adaptive step-sizes
- Handling nonpositive curvature in a limited memory steepest descent method
- Hybrid deterministic-stochastic methods for data fitting
- New adaptive stepsize selections in gradient methods
- On the steplength selection in gradient methods for unconstrained optimization
- On the steplength selection in stochastic gradient methods
- Optimization methods for large-scale machine learning
- Sample size selection in optimization methods for machine learning
Cited in
(8)- Linesearch Newton-CG methods for convex optimization with noise
- To the special issue dedicated to the 3rd international conference ``Numerical computations: theory and algorithms -- NUMTA 2019 June 15--21, 2019, Isola Capo Rizzuto, Italy
- On stochastic gradient and subgradient methods with adaptive steplength sequences
- On the Barzilai and Borwein choice of steplength for the gradient method
- A line search based proximal stochastic gradient algorithm with dynamical variance reduction
- Explainable bilevel optimization: an application to the Helsinki Deblur Challenge
- Value iteration for streaming data on a continuous space with gradient method in an RKHS
- Limited memory gradient methods for unconstrained optimization
This page was built for publication: Ritz-like values in steplength selections for stochastic gradient methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2156893)
