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

arXiv: https://arxiv.org/abs/2502.20153 · HTML: https://mlsanity.com/paper/2502.20153/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 20 of 20)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms](https://mlsanity.com/paper/1901.10912/) (2019)
- [Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE](https://mlsanity.com/paper/2103.10022/) (2021)
- [Causal Bandits: Learning Good Interventions via Causal Inference](https://mlsanity.com/paper/1606.03203/) (2016)
- [Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey](https://mlsanity.com/paper/2112.08936/) (2021)
- [Identifiability of deep generative models without auxiliary information](https://mlsanity.com/paper/2206.10044/) (2022)
- [Multi-Task Learning for Contextual Bandits](https://mlsanity.com/paper/1705.08618/) (2017)
- [Latent Bandits Revisited](https://mlsanity.com/paper/2006.08714/) (2020)
- [Causal Bandits with Unknown Graph Structure](https://mlsanity.com/paper/2106.02988/) (2021)
- [A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Models](https://mlsanity.com/paper/2102.06648/) (2021)
- [Contextual Bandits with Latent Confounders: An NMF Approach](https://mlsanity.com/paper/1606.00119/) (2016)
- [Transfer Learning for Contextual Multi-armed Bandits](https://mlsanity.com/paper/2211.12612/) (2022)
- [Latent Contextual Bandits and their Application to Personalized Recommendations for New Users](https://mlsanity.com/paper/1604.06743/) (2016)
- [Adaptively Exploiting d-Separators with Causal Bandits](https://mlsanity.com/paper/2202.05100/) (2022)
- [Causal Bandits with General Causal Models and Interventions](https://mlsanity.com/paper/2403.00233/) (2024)

## Built on by (most cited first, 4 of 4)

- [Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift](https://mlsanity.com/paper/2505.17203/) (2025)
- [On Transportability for Structural Causal Bandits](https://mlsanity.com/paper/2511.17953/) (2025)
- [Asymptotically Optimal Problem-Dependent Bandit Policies for Transfer Learning](https://mlsanity.com/paper/2509.19098/) (2025)
- [Jump Start or False Start? A Theoretical and Empirical Evaluation of LLM-initialized Bandits](https://mlsanity.com/paper/2604.02527/) (2026)

## Abstract (arXiv)

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.