Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportability

TL;DR

This paper introduces a causal inference-based transfer learning framework for latent contextual bandits under covariate shift, improving learning efficiency by avoiding negative transfer through effective knowledge transfer.

Contribution

It develops algorithms that leverage causal transportability and variational autoencoders to transfer relevant knowledge in high-dimensional proxy settings, addressing negative transfer.

Findings

Empirically improved learning efficiency on synthetic datasets.

Effective knowledge transfer reduces negative transfer.

Demonstrates the utility of causal transportability in bandit settings.

Abstract

Transferring knowledge from one environment to another is an essential ability of intelligent systems. Nevertheless, when two environments are different, naively transferring all knowledge may deteriorate the performance, a phenomenon known as negative transfer. In this paper, we address this issue within the framework of multi-armed bandits from the perspective of causal inference. Specifically, we consider transfer learning in latent contextual bandits, where the actual context is hidden, but a potentially high-dimensional proxy is observable. We further consider a covariate shift in the context across environments. We show that naively transferring all knowledge for classical bandit algorithms in this setting led to negative transfer. We then leverage transportability theory from causal inference to develop algorithms that explicitly transfer effective knowledge for estimating the causal effects of interest in the target environment. Besides, we utilize variational autoencoders to approximate causal effects under the presence of a high-dimensional proxy. We test our algorithms on synthetic and semi-synthetic datasets, empirically demonstrating consistently improved learning efficiency across different proxies compared to baseline algorithms, showing the effectiveness of our causal framework in transferring knowledge.