# Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits

arXiv: https://arxiv.org/abs/2609.09907 · HTML: https://mlsanity.com/paper/2609.09907/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 9 Sep 2026.

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

- [Adaptive Gradient-Based Meta-Learning Methods](https://mlsanity.com/paper/1906.02717/) (2019)
- [Meta-learning of Sequential Strategies](https://mlsanity.com/paper/1905.03030/) (2019)
- [Meta-Thompson Sampling](https://mlsanity.com/paper/2102.06129/) (2021)
- [Impact of Representation Learning in Linear Bandits](https://mlsanity.com/paper/2010.06531/) (2020)
- [Meta-learning with Stochastic Linear Bandits](https://mlsanity.com/paper/2005.08531/) (2020)
- [Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits](https://mlsanity.com/paper/2002.00287/) (2020)
- [First- and Second-Order Bounds for Adversarial Linear Contextual Bandits](https://mlsanity.com/paper/2305.00832/) (2023)
- [Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits](https://mlsanity.com/paper/2309.00814/) (2023)
- [Metalearning Linear Bandits by Prior Update](https://mlsanity.com/paper/2107.05320/) (2021)
- [Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms](https://mlsanity.com/paper/2202.13001/) (2022)
- [Meta-Learning Adversarial Bandit Algorithms](https://mlsanity.com/paper/2307.02295/) (2023)
- [Meta-strategy for Learning Tuning Parameters with Guarantees](https://mlsanity.com/paper/2102.02504/) (2021)
- [Adversarial Contextual Bandits Go Kernelized](https://mlsanity.com/paper/2310.01609/) (2023)
- [Sparse Sampling for Inverse Problems with Tensors](https://mlsanity.com/paper/1806.10976/) (2018)
- [LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits](https://mlsanity.com/paper/2403.03219/) (2024)
- [Meta Learning in Bandits within Shared Affine Subspaces](https://mlsanity.com/paper/2404.00688/) (2024)
- [An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction](https://mlsanity.com/paper/2508.11931/) (2025)
- [Online Meta-Learning in Adversarial Multi-Armed Bandits](https://mlsanity.com/paper/2205.15921/) (2022)
- [Fast Sampling for Linear Inverse Problems of Vectors and Tensors using Multilinear Extensions](https://mlsanity.com/paper/2312.01574/) (2023)
- [A Classification View on Meta Learning Bandits](https://mlsanity.com/paper/2504.04505/) (2025)

## Abstract (arXiv)

Meta-learning has emerged as an effective paradigm for transferring knowledge across sequential bandit tasks. While substantial progress has been made for stochastic bandits and non-contextual adversarial bandits, meta-learning for adversarial linear contextual bandits (ALCBs) with random action sets remains largely unexplored. To address this problem, we propose Meta-LinEXP3, an online-within-online algorithm that constructs a predictable task-level prior from completed tasks to guide the inner LinEXP3 learner. For known context distributions, we develop a policy-centered estimator that achieves an intrinsic-dimension O(√n) per-task regret bound. For unknown distributions, we introduce a past-only regularized moment estimator with an O(n2/3) leading regret term and explicit finite-sample error. We further establish a direct connection between prior accuracy and transfer regret, showing that increasingly accurate priors yield sublinear transfer-dependent regret across tasks. Experiments demonstrate the effectiveness of Meta-LinEXP3, including its application to structured hyperspectral tensor sampling.