Online non-convex optimization with imperfect feedback
arXiv:2010.08496
Abstract
We consider the problem of online learning with non-convex losses. In terms of feedback, we assume that the learner observes - or otherwise constructs - an inexact model for the loss function encountered at each stage, and we propose a mixed-strategy learning policy based on dual averaging. In this general context, we derive a series of tight regret minimization guarantees, both for the learner's static (external) regret, as well as the regret incurred against the best dynamic policy in hindsight. Subsequently, we apply this general template to the case where the learner only has access to the actual loss incurred at each stage of the process. This is achieved by means of a kernel-based estimator which generates an inexact model for each round's loss function using only the learner's realized losses as input.
arXiv comment30 pages, 2 figures, 1 table
References in corpus (6)
- Community detection in graphs
- Mirror Descent Meets Fixed Share (and feels no regret)
- Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution
- Efficient Regret Minimization in Non-Convex Games
- Multi-agent online learning in time-varying games
- Regret minimization in stochastic non-convex learning via a proximal-gradient approach