DeepAI AI Chat
Log In Sign Up

Warm Starting Bandits with Side Information from Confounded Data

by   Nihal Sharma, et al.
The University of Texas at Austin

We study a variant of the multi-armed bandit problem where side information in the form of bounds on the mean of each arm is provided. We describe how these bounds on the means can be used efficiently for warm starting bandits. Specifically, we propose the novel UCB-SI algorithm, and illustrate improvements in cumulative regret over the standard UCB algorithm, both theoretically and empirically, in the presence of non-trivial side information. As noted in (Zhang Bareinboim, 2017), such information arises, for instance, when we have prior logged data on the arms, but this data has been collected under a policy whose choice of arms is based on latent variables to which access is no longer available. We further provide a novel approach for obtaining such bounds from prior partially confounded data under some mild assumptions. We validate our findings through semi-synthetic experiments on data derived from real datasets.


page 1

page 2

page 3

page 4


Thompson Sampling for Bandits with Clustered Arms

We propose algorithms based on a multi-level Thompson sampling scheme, f...

Stochastic Multi-Armed Bandits with Control Variates

This paper studies a new variant of the stochastic multi-armed bandits p...

Thresholding Graph Bandits with GrAPL

In this paper, we introduce a new online decision making paradigm that w...

Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications

We study combinatorial multi-armed bandit with probabilistically trigger...

Combinatorial Bandits under Strategic Manipulations

We study the problem of combinatorial multi-armed bandits (CMAB) under s...

Stochastic Rising Bandits

This paper is in the field of stochastic Multi-Armed Bandits (MABs), i.e...

Max-Utility Based Arm Selection Strategy For Sequential Query Recommendations

We consider the query recommendation problem in closed loop interactive ...