Loading
Life sciences · Preprint
arXiv · September 9, 2026
Raises a question worth testing. It does not answer one.
Meta-LinEXP3 is a proposed meta-learning algorithm for adversarial linear contextual bandits with theoretical regret bounds under known and unknown context distributions. The work is foundational in machine learning theory and does not constitute evidence for clinical practice or established empirical claims.
Preprint. Intervention: Meta-LinEXP3 algorithm: online-within-online meta-learner with policy-centered estimator (known distributions) and regularized moment estimator (unknown distributions).
Policy-centered estimator achieves O(√n) per-task regret bound for known context distributions Regularized moment estimator achieves O(n^(2/3)) leading regret term for unknown distributions with explicit finite-sample error Direct connection demonstrated between prior accuracy and transfer-dependent regret across tasks
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is a theoretical computer science contribution proposing a novel algorithm with regret bounds and limited experimental validation; it raises and addresses a computational learning problem rather than answering a clinical or established empirical question.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
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 $\mathcal{O}(\sqrt{n})$ per-task regret bound. For unknown distributions, we introduce a past-only regularized moment estimator with an $\mathcal{O}(n^{2/3})$ 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.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.