Search Results for author: Jialin Yi

Found 5 papers, 0 papers with code

Regret-Minimization Algorithms for Multi-Agent Cooperative Learning Systems

no code implementations30 Oct 2023 Jialin Yi

The regret bounds I present in Chapter 3, 4 and 5 quantify how the regret depends on the connectivity of the communication network and the communication delay, thus giving useful guidance on design of the communication protocol in MACL systems

Cloud Computing Decision Making

Doubly Adversarial Federated Bandits

no code implementations22 Jan 2023 Jialin Yi, Milan Vojnović

For the bandit feedback setting, we propose a near-optimal federated bandit algorithm called FEDEXP3.

Open-Ended Question Answering

On Regret-optimal Cooperative Nonstochastic Multi-armed Bandits

no code implementations30 Nov 2022 Jialin Yi, Milan Vojnović

We show that with suitable regularizers and communication protocols, a collaborative multi-agent \emph{follow-the-regularized-leader} (FTRL) algorithm has an individual regret upper bound that matches the lower bound up to a constant factor when the number of arms is large enough relative to degrees of agents in the communication graph.

Multi-Armed Bandits

Automatic Loss Function Search for Predict-Then-Optimize Problems with Strong Ranking Property

no code implementations ICLR 2022 Boshi Wang, Jialin Yi, Hang Dong, Bo Qiao, Chuan Luo, QIngwei Lin

Combinatorial optimization problems with parameters to be predicted from side information are commonly seen in a variety of problems during the paradigm shift from reactive decision making to proactive decision making.

Combinatorial Optimization Decision Making

Pure Exploration and Regret Minimization in Matching Bandits

no code implementations31 Jul 2021 Flore Sentenac, Jialin Yi, Clément Calauzènes, Vianney Perchet, Milan Vojnovic

Finding an optimal matching in a weighted graph is a standard combinatorial problem.

Cannot find the paper you are looking for? You can Submit a new open access paper.