Perturbation techniques in online learning and optimization
From MaRDI portal
Recommendations
- Algorithmic Learning Theory
- Following the Perturbed Leader to Gamble at Multi-armed Bandits
- Online learning in case of unbounded losses using follow the perturbed leader algorithm
- Stochastic Algorithms: Foundations and Applications
- Online convex optimization in the bandit setting: gradient descent without a gradient
Cited in
(12)- Perturbation scheme for online learning of features: Incremental principal component analysis
- Beyond the hazard rate: more perturbation algorithms for adversarial multi-armed bandits
- Perturbations, optimization, and statistics
- Online learning to rank with top-k feedback
- scientific article; zbMATH DE number 1569102 (Why is no real title available?)
- Tsallis-INF: an optimal algorithm for stochastic and adversarial bandits
- Stochastic Algorithms: Foundations and Applications
- Leveraging randomized smoothing for optimal control of nonsmooth dynamical systems
- Learning in random utility models via online decision problems
- On the complexity of computing sparse equilibria and lower bounds for no-regret learning in games
- Follow-the-perturbed-leader achieves best-of-both-worlds for bandit problems
- Online non-convex learning: following the perturbed leader is optimal
This page was built for publication: Perturbation techniques in online learning and optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3295539)
