Online non-convex optimization with imperfect feedback - Archive ouverte HAL Access content directly
Conference Papers Year :

Online non-convex optimization with imperfect feedback

(1) , (1) , (2, 1) , (1)
1
2
Amélie Héliou
  • Function : Author
  • PersonId : 1084692
Matthieu Martin
  • Function : Author
  • PersonId : 1084693
Thibaud Rahier
  • Function : Author
  • PersonId : 1084694

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.
Fichier principal
Vignette du fichier
OnlineNonConvex-NIPS.pdf (952.43 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03043746 , version 1 (07-12-2020)

Identifiers

  • HAL Id : hal-03043746 , version 1

Cite

Amélie Héliou, Matthieu Martin, Panayotis Mertikopoulos, Thibaud Rahier. Online non-convex optimization with imperfect feedback. NeurIPS 2020 - 34th International Conference on Neural Information Processing Systems, 2020, Vancouver, Canada. ⟨hal-03043746⟩
59 View
251 Download

Share

Gmail Facebook Twitter LinkedIn More