@inproceedings{deshpande2017accurate,
author = {Deshpande, Yash and Mackey, Lester and Syrgkanis, Vasilis and Taddy, Matt},
title = {Accurate Inference for Adaptive Linear Models},
booktitle = {International Conference on Machine Learning (ICML)},
year = {2017},
month = {December},
abstract = {Estimators computed from adaptively collected data do not behave like their non-adaptive brethren. Rather, the sequential dependence of the collection policy can lead to severe distributional biases that persist even in the infinite data limit. We develop a general method -- W-decorrelation -- for transforming the bias of adaptive linear regression estimators into variance. The method uses only coarse-grained information about the data collection policy and does not need access to propensity scores or exact knowledge of the policy. We bound the finite-sample bias and variance of W-decorrelation and develop asymptotically correct confidence intervals based on a novel martingale central limit theorem. We then demonstrate the empirical benefits of the generic W-decorrelation procedure in two different adaptive data settings: the multi-armed bandit and the autoregressive time series settings.},
url = {http://approjects.co.za/?big=en-us/research/publication/accurate-inference-for-adaptive-linear-models/},
}