Accurate Inference for Adaptive Linear Models


Yash Deshpande, Lester Mackey, Vasilis Syrgkanis, Matt Taddy ;
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:1202-1211, 2018.


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 – $\mathbf{W}$-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 the $\mathbf{W}$-estimator and develop asymptotically correct confidence intervals based on a novel martingale central limit theorem. We then demonstrate the empirical benefits of the generic $\mathbf{W}$-decorrelation procedure in two different adaptive data settings: the multi-armed bandit and the autoregressive time series.

Related Material