A new regret analysis for Adam-type algorithms - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

A new regret analysis for Adam-type algorithms


In this paper, we focus on a theory-practice gap for Adam and its variants (AMSgrad, AdamNC, etc.). In practice, these algorithms are used with a constant first-order moment parameter β 1 (typically between 0.9 and 0.99). In theory, regret guarantees for online convex optimization require a rapidly decaying β 1 → 0 schedule. We show that this is an artifact of the standard analysis, and we propose a novel framework that allows us to derive optimal, data-dependent regret bounds with a constant β 1 , without further assumptions. We also demonstrate the flexibility of our analysis on a wide range of different algorithms and settings.
Fichier principal
Vignette du fichier
ICML-2020-a-new-regret-analysis-for-adam-type-algorithms-Paper.pdf (259.28 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03043697 , version 1 (07-12-2020)


  • HAL Id : hal-03043697 , version 1


Ahmet Alacaoglu, Yura Malitsky, Panayotis Mertikopoulos, Volkan Cevher. A new regret analysis for Adam-type algorithms. ICML 2020 - 37th International Conference on Machine Learning, Jul 2020, Vienna, Austria. pp.1-10. ⟨hal-03043697⟩
64 View
154 Download


Gmail Facebook X LinkedIn More