Meta representation learning with contextual linear bandits

DOI10.1214/25-STS994MaRDI QIDQ6909434zbMATH OpenFDO

Authors Leonardo Cella, K. Lounici, Grégoire Pacreau, Massimiliano Pontil

Publication date 29 October 2025

Published in Statistical Science (Search for Journal in Brave)

Full work available at URL https://projecteuclid.org/journals/statistical-science/volume-40/issue-3/Meta-Representation-Learning-with-Contextual-Linear-Bandits/10.1214/25-STS994.full

zbMATH Keywords

contextual banditlow-rank matrixmeta learningmulti-taskrepresentation learningtrace norm regularization

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• 10.1162/153244303321897663
• 10.1162/153244304322765658
• A no-free-lunch theorem for multitask learning
• Adaptive and robust multi-task learning
• An Efficient Method of Estimating Seemingly Unrelated Regressions and Tests for Aggregation Bias
• Bandit algorithms
• Bounds for linear multi-task learning
• Concentration inequalities for sums and martingales
• Convex multi-task feature learning
• Econometric analysis of cross section and panel data.
• Estimation of (near) low-rank matrices with noise and high-dimensional scaling
• Estimation of high-dimensional low-rank matrices
• Hanson-Wright inequality and sub-Gaussian concentration
• High-dimensional probability. An introduction with applications in data science
• scientific article; zbMATH DE number 5957307 (Why is no real title available?)
• scientific article; zbMATH DE number 1448976 (Why is no real title available?)
• Marketing models of consumer heterogeneity
• Matrix completion by singular value thresholding: sharp bounds
• Meta representation learning with contextual linear bandits
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• Online decision making with high-dimensional covariates
• Oracle inequalities and optimal inference under group sparsity
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Perturbation of linear forms of singular vectors under Gaussian noise
• Statistics for high-dimensional data. Methods, theory and applications.
• Support union recovery in high-dimensional multivariate regression
• The benefit of multitask representation learning
• Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method

Cited in

(2)

• Meta representation learning with contextual linear bandits
• Editorial: Special issue on ``Learning across distribution shifts

This page was built for publication: Meta representation learning with contextual linear bandits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6909434)