Timezone: »

 
Spotlight
Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback
Tianyi Lin · Aldo Pacchiano · Yaodong Yu · Michael Jordan

Tue Jul 19 08:55 AM -- 09:00 AM (PDT) @ Room 309
in Theory: Online Learning/Bandits »
Motivated by applications to online learning in sparse estimation and Bayesian optimization, we consider the problem of online unconstrained nonsubmodular minimization with delayed costs in both full information and bandit feedback settings. In contrast to previous works on online unconstrained submodular minimization, we focus on a class of nonsubmodular functions with special structure, and prove regret guarantees for several variants of the online and approximate online bandit gradient descent algorithms in static and delayed scenarios. We derive bounds for the agent's regret in the full information and bandit feedback setting, even if the delay between choosing a decision and receiving the incurred cost is unbounded. Key to our approach is the notion of $(\alpha, \beta)$-regret and the extension of the generic convex relaxation model from~\citet{El-2020-Optimal}, the analysis of which is of independent interest. We conduct and showcase several simulation studies to demonstrate the efficacy of our algorithms.
Keywords: T: Online Learning and Bandits · MISC: Supervised Learning · MISC: Online Learning, Active Learning and Bandits

Author Information

Tianyi Lin (University of California, Berkeley)
Aldo Pacchiano (Microsoft Research)
Yaodong Yu (University of California, Berkeley)
Michael Jordan (UC Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors