Log In Sign Up

Near-optimal inference in adaptive linear regression

by   Koulik Khamaru, et al.

When data is collected in an adaptive manner, even simple methods like ordinary least squares can exhibit non-normal asymptotic behavior. As an undesirable consequence, hypothesis tests and confidence intervals based on asymptotic normality can lead to erroneous results. We propose an online debiasing estimator to correct these distributional anomalies in least squares estimation. Our proposed method takes advantage of the covariance structure present in the dataset and provides sharper estimates in directions for which more information has accrued. We establish an asymptotic normality property for our proposed online debiasing estimator under mild conditions on the data collection process, and provide asymptotically exact confidence intervals. We additionally prove a minimax lower bound for the adaptive linear regression problem, thereby providing a baseline by which to compare estimators. There are various conditions under which our proposed estimator achieves the minimax lower bound up to logarithmic factors. We demonstrate the usefulness of our theory via applications to multi-armed bandit, autoregressive time series estimation, and active learning with exploration.


page 1

page 2

page 3

page 4


Accurate Inference for Adaptive Linear Models

Estimators computed from adaptively collected data do not behave like th...

Statistical Inference with M-Estimators on Bandit Data

Bandit algorithms are increasingly used in real world sequential decisio...

A Pseudo-Likelihood Approach to Linear Regression with Partially Shuffled Data

Recently, there has been significant interest in linear regression in th...

Sparse Nonlinear Regression: Parameter Estimation and Asymptotic Inference

We study parameter estimation and asymptotic inference for sparse nonlin...

Linear regression with stationary errors : the R package slm

This paper introduces the R package slm which stands for Stationary Line...

Post-Contextual-Bandit Inference

Contextual bandit algorithms are increasingly replacing non-adaptive A/B...

Efficient two-sample functional estimation and the super-oracle phenomenon

We consider the estimation of two-sample integral functionals, of the ty...