Near-optimal inference in adaptive linear regression

DOI10.1214/24-AOS2450MaRDI QIDQ6868473zbMATH OpenFDO

Authors Koulik Khamaru, Yash Deshpande, Tor Lattimore, Lester Mackey, Martin J. Wainwright

Publication date 26 January 2026

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://projecteuclid.org/journals/annals-of-statistics/volume-53/issue-6/Near-optimal-inference-in-adaptive-linear-regression/10.1214/24-AOS2450.full

zbMATH Keywords

adaptive linear regressionasymptotic normalityautoregressive time seriesminimax lower boundmulti-armed banditsonline debiasing

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20) Parametric tolerance and confidence regions (62F25) Linear regression; mixed models (62J05)

Cites work

• Adaptive design and stochastic approximation
• Asymptotic properties of nonlinear least squares estimates in stochastic regression models
• Bandit algorithms
• Concentration inequalities. A nonasymptotic theory of independence
• Confidence intervals for policy evaluation in adaptive experiments
• Distribution of the Estimators for Autoregressive Time Series With a Unit Root
• Dynamic system identification. Experiment design and data analysis
• High-dimensional statistics. A non-asymptotic viewpoint
• scientific article; zbMATH DE number 7626761 (Why is no real title available?)
• scientific article; zbMATH DE number 3405266 (Why is no real title available?)
• Introduction to stochastic control theory
• Least squares estimates in stochastic regression models with applications to identification and control of dynamic systems
• Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges
• Near-optimal inference in adaptive linear regression
• On the bias, risk, and consistency of sample means in multi-armed bandits
• On the likelihood that one unkrown probability exeeds another in view of the evidence of two samples.
• Strong consistency of least squares estimates in multiple regression II
• The Limiting Distribution of the Serial Correlation Coefficient in the Explosive Case
• Time series analysis. Forecasting and control
• Time-uniform, nonparametric, nonasymptotic confidence sequences

Cited in

(1)

• Near-optimal inference in adaptive linear regression

This page was built for publication: Near-optimal inference in adaptive linear regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6868473)