Stochastic Online Learning with Probabilistic Graph Feedback

03/04/2019
by   Shuai Li, et al.
20

We consider a problem of stochastic online learning with general probabilistic graph feedback. Two cases are covered. (a) The one-step case where for each edge (i,j) with probability p_ij in the probabilistic feedback graph. After playing arm i the learner observes a sample reward feedback of arm j with independent probability p_ij. (b) The cascade case where after playing arm i the learner observes feedback of all arms j in a probabilistic cascade starting from i -- for each (i,j) with probability p_ij, if arm i is played or observed, then a reward sample of arm j would be observed with independent probability p_ij. Previous works mainly focus on deterministic graphs which corresponds to one-step case with p_ij∈{0,1}, an adversarial sequence of graphs with certain topology guarantees or a specific type of random graphs. We analyze the asymptotic lower bounds and design algorithms in both cases. The regret upper bounds of the algorithms match the lower bounds with high probability.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/23/2016

Online Learning with Feedback Graphs Without the Graphs

We study an online learning framework introduced by Mannor and Shamir (2...
research
01/11/2021

Learning with Comparison Feedback: Online Estimation of Sample Statistics

We study an online version of the noisy binary search problem where feed...
research
08/29/2023

Pure Exploration under Mediators' Feedback

Stochastic multi-armed bandits are a sequential-decision-making framewor...
research
03/09/2016

Best-of-K Bandits

This paper studies the Best-of-K Bandit game: At each time the player ch...
research
09/06/2021

Online Learning of Independent Cascade Models with Node-level Feedback

We propose a detailed analysis of the online-learning problem for Indepe...
research
06/16/2022

Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback

The problem of online learning with graph feedback has been extensively ...
research
10/09/2022

Learning on the Edge: Online Learning with Stochastic Feedback Graphs

The framework of feedback graphs is a generalization of sequential decis...

Please sign up or login with your details

Forgot password? Click here to reset