Cautious regret minimization: Online optimization with long-term budget constraints - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2019

Cautious regret minimization: Online optimization with long-term budget constraints

Abstract

We study a class of online convex optimization problems with long-term budget constraints that arise naturally as reliability guarantees or total consumption constraints. In this general setting, prior work by Mannor et al. (2009) has shown that achieving no regret is impossible if the functions defining the agent's budget are chosen by an adversary. To overcome this obstacle, we refine the agent's regret metric by introducing the notion of a "K-benchmark", i.e., a comparator which meets the problem's allotted budget over any window of length K. The impossibility analysis of Mannor et al. (2009) is recovered when K = T ; however, for K = o(T), we show that it is possible to minimize regret while still meeting the problem's long-term budget constraints. We achieve this via an online learning algorithm based on cautious online Lagrangian descent (COLD) for which we derive explicit bounds, in terms of both the incurred regret and the residual budget violations.
Fichier principal
Vignette du fichier
BudgetRegret-ICML.pdf (708.05 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02405753 , version 1 (11-12-2019)

Identifiers

  • HAL Id : hal-02405753 , version 1

Cite

Nikolaos Liakopoulos, Apostolos S Destounis, Georgios Paschos, Thrasyvoulos Spyropoulos, Panayotis Mertikopoulos. Cautious regret minimization: Online optimization with long-term budget constraints. ICML 2019 - 36th International Conference on Machine Learning, Jun 2019, Long Beach, United States. pp.1-9. ⟨hal-02405753⟩
94 View
146 Download

Share

Gmail Facebook X LinkedIn More