Skip to Main content Skip to Navigation
Conference papers

Zeroth-order non-convex learning via hierarchical dual averaging

Abstract : We propose a hierarchical version of dual averaging for zeroth-order online non-convex optimization-i.e., learning processes where, at each stage, the optimizer is facing an unknown non-convex loss function and only receives the incurred loss as feedback. The proposed class of policies relies on the construction of an online model that aggregates loss information as it arrives, and it consists of two principal components: (a) a regularizer adapted to the Fisher information metric (as opposed to the metric norm of the ambient space); and (b) a principled exploration of the problem's state space based on an adapted hierarchical schedule. This construction enables sharper control of the model's bias and variance, and allows us to derive tight bounds for both the learner's static and dynamic regret-i.e., the regret incurred against the best dynamic policy in hindsight over the horizon of play.
Document type :
Conference papers
Complete list of metadata
Contributor : Panayotis Mertikopoulos Connect in order to contact the contributor
Submitted on : Monday, September 13, 2021 - 9:44:19 AM
Last modification on : Wednesday, July 6, 2022 - 4:24:40 AM


Files produced by the author(s)


  • HAL Id : hal-03341912, version 1


Amélie Héliou, Matthieu Martin, Thibaud Rahier, Panayotis Mertikopoulos. Zeroth-order non-convex learning via hierarchical dual averaging. ICML 2021 - 38th International Conference on Machine Learning, Jul 2021, Vienna, Austria. pp.1-34. ⟨hal-03341912⟩



Record views


Files downloads