Back to search

University of Victoria (Canada)

Stochastically constrained adversarial lifelong learning

Abstract

dc:description.abstract

Lifelong learning is a setting of online learning where there is a sequence of tasks and each task is an online learning problem. The lifelong learning algorithm is split into two sections: the meta-level and the within-task level. In this thesis, we explore an online learning setting with a stochastically-constrained adversarial (SCA) assumption. The SCA assumption is that there is not a singular representation that works the best for each of the tasks in terms of minimizing expected losses, but that there is a representation that will become better than all other representations on average over all tasks after enough tasks have been complete. We show that in the single task setting, Decreasing Hedge with perturbed losses achieves best-of-both-worlds regret bounds under the SCA assumption. In the lifelong learning setting, we propose an algorithm with Decreasing Hedge in the meta-level and Squint in the within-task level. Under the SCA assumption in the meta-level and the Bernstein condition in the within-task level, this lifelong learning algorithm achieves best-of-both-worlds regret bounds.

Degree

thesis:*
Level thesis:degree_level
Master of Science MSc
Department thesis:degree_department
Department of Computer Science
Year dc:date.issued
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Grant-Hagen, Mica
Advisor dc:contributor.supervisor
  • Mehta, Nishant

Subjects

dc:subject × 3

Rights

dc:rights
Statement dc:rights
  • Available to the World Wide Web
Language dc:language.iso
en, English

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1828/23960

Chain of custody

source
Harvested from
University of Victoria (Canada)
Base URL
dspace.library.uvic.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Grant-Hagen, Mica. Stochastically constrained adversarial lifelong learning. Master of Science MSc thesis, 2026. https://hdl.handle.net/1828/23960