# Hypothesis Transfer in Bandits by Weighted Models

arXiv: https://arxiv.org/abs/2211.07387 · HTML: https://mlsanity.com/paper/2211.07387/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 14 Nov 2022.

## Builds on (most cited first, 8 of 8)

- [Weighted Linear Bandits for Non-Stationary Environments](https://mlsanity.com/paper/1909.09146/) (2019)
- [Sequential Transfer in Multi-armed Bandit with Finite Set of Models](https://mlsanity.com/paper/1307.6887/) (2013)
- [Hypothesis Transfer Learning via Transformation Functions](https://mlsanity.com/paper/1612.01020/) (2016)
- [Stochastic Multi-armed Bandits in Constant Space](https://mlsanity.com/paper/1712.09007/) (2017)
- [Fast Rates by Transferring from Auxiliary Hypotheses](https://mlsanity.com/paper/1412.1619/) (2014)
- [Handling Concept Drift via Model Reuse](https://mlsanity.com/paper/1809.02804/) (2018)
- [Self-Tuning Bandits over Unknown Covariate-Shifts](https://mlsanity.com/paper/2007.08584/) (2020)
- [Memory-Constrained No-Regret Learning in Adversarial Bandits](https://mlsanity.com/paper/2002.11804/) (2020)

## Built on by (most cited first, 2 of 2)

- [Meta Learning in Bandits within Shared Affine Subspaces](https://mlsanity.com/paper/2404.00688/) (2024)
- [Direction-Aware Offline-to-Online Learning in Linear Contextual Bandits](https://mlsanity.com/paper/2604.24016/) (2026)

## Abstract (arXiv)

We consider the problem of contextual multi-armed bandits in the setting of hypothesis transfer learning. That is, we assume having access to a previously learned model on an unobserved set of contexts, and we leverage it in order to accelerate exploration on a new bandit problem. Our transfer strategy is based on a re-weighting scheme for which we show a reduction in the regret over the classic Linear UCB when transfer is desired, while recovering the classic regret rate when the two tasks are unrelated. We further extend this method to an arbitrary amount of source models, where the algorithm decides which model is preferred at each time step. Additionally we discuss an approach where a dynamic convex combination of source models is given in terms of a biased regularization term in the classic LinUCB algorithm. The algorithms and the theoretical analysis of our proposed methods substantiated by empirical evaluations on simulated and real-world data.