Doubly Adversarial Federated Bandits
24. července 2023
Řečníci
Milan Vojnovic
Řečník · 0 sledujících
O prezentaci
We study a new non-stochastic federated multiarmed bandit problem with multiple agents collaborating via a communication network. The losses of the arms are assigned by an oblivious adversary that specifies the loss of each arm not only for each time step but also for each agent, which we call “doubly adversarial”. In this setting, different agents may choose the same arm in the same time step but observe different feedback. The goal of each agent is to find a globally best arm in hindsight that has the lowest cumulative loss averaged over all agents, which necessities the communication among agents. We provide regret lower bounds for any federated bandit algorithm under different settings, when agents have access to full-information feedback, or the bandit feedback. For the bandit feedback setting, we propose a near-optimal federated bandit algorithm called FEDEXP3. Our algorithm gives a positive answer to an open question proposed in (Cesa-Bianchi et al., 2016): FEDEXP3 can guarantee a sub-linear regret without exchanging sequences of selected arm identities or loss sequences among agents. We also provide numerical evaluations of our algorithm to validate our theoretical results and demonstrate its effectiveness on synthetic and real-world datasets.We study a new non-stochastic federated multiarmed bandit problem with multiple agents collaborating via a communication network. The losses of the arms are assigned by an oblivious adversary that specifies the loss of each arm not only for each time step but also for each agent, which we call “doubly adversarial”. In this setting, different agents may choose the same arm in the same time step but observe different feedback. The goal of each agent is to find a globally best arm in hindsight that…
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization
Zhlédnout později
Xufeng Cai, …
Constrained Decision Transformer for Offline Safe Reinforcement Learning
Zhlédnout později
Zuxin Liu, …
Competitive Gradient Optimisation
Zhlédnout později
Learning to Optimize Differential Games
Zhlédnout později
Xuxi Chen, …
Demystifying Disagreement-on-the-Line in High Dimensions
Zhlédnout později
Donghwan Lee, …
