2022/07/16 by Nikolai Karpov, Qin Zhang, Karpov, Nikolai +1 · 1 citation
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Auction Theory and Applications #Data Structures and Algorithms (cs.DS) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms
paper · pdf · doi:10.48550/arxiv.2207.08015
openalex publication_date 2022/07/16 · openalex created_date 2022/07/21 · openalex updated_date 2026/07/28
In this paper, we study the tradeoffs between the time and the number of communication rounds of the best arm identification problem in the heterogeneous collaborative learning model, where multiple agents interact with possibly different environments and they want to learn in parallel an objective function in the aggregated environment. By proving almost tight upper and lower bounds, we show that collaborative learning in the heterogeneous setting is inherently more difficult than that in the homogeneous setting in terms of the time-round tradeoff.