Collaborative Top Distribution Identifications with Limited Interaction

04/20/2020
by   Nikolai Karpov, et al.
0

We consider the following problem in this paper: given a set of n distributions, find the top-m ones with the largest means. This problem is also called top-m arm identifications in the literature of reinforcement learning, and has numerous applications. We study the problem in the collaborative learning model where we have multiple agents who can draw samples from the n distributions in parallel. Our goal is to characterize the tradeoffs between the running time of learning process and the number of rounds of interaction between agents, which is very expensive in various scenarios. We give optimal time-round tradeoffs, as well as demonstrate complexity separations between top-1 arm identification and top-m arm identifications for general m and between fixed-time and fixed-confidence variants. As a byproduct, we also give an algorithm for selecting the distribution with the m-th largest mean in the collaborative learning model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/16/2022

Collaborative Best Arm Identification with Limited Communication on Non-IID Data

In this paper, we study the tradeoffs between time-speedup and the numbe...
research
08/24/2022

Collaborative Algorithms for Online Personalized Mean Estimation

We consider an online estimation problem involving a set of agents. Each...
research
04/05/2019

Collaborative Learning with Limited Interaction: Tight Bounds for Distributed Exploration in Multi-Armed Bandits

Best arm identification (or, pure exploration) in multi-armed bandits is...
research
06/09/2022

Globally Optimal Algorithms for Fixed-Budget Best Arm Identification

We consider the fixed-budget best arm identification problem where the g...
research
08/18/2022

Communication-Efficient Collaborative Best Arm Identification

We investigate top-m arm identification, a basic problem in bandit theor...
research
04/11/2022

Approximate Top-m Arm Identification with Heterogeneous Reward Variances

We study the effect of reward variance heterogeneity in the approximate ...
research
02/09/2021

Backdoor Scanning for Deep Neural Networks through K-Arm Optimization

Back-door attack poses a severe threat to deep learning systems. It inje...

Please sign up or login with your details

Forgot password? Click here to reset