Off-policy estimation with adaptively collected data: the power of online learning

• URL: http://arxiv.org/abs/2411.12786v1
• Date: Tue, 19 Nov 2024 10:18:27 GMT
• Title: Off-policy estimation with adaptively collected data: the power of online learning
• Authors: Jeonghwan Lee, Cong Ma,
• Abstract summary: We consider estimation of a linear functional of the treatment effect using adaptively collected data. We propose a general reduction scheme that allows one to produce a sequence of estimates for the treatment effect via online learning.
• Score: 20.023469636707635
• License:
• Abstract: We consider estimation of a linear functional of the treatment effect using adaptively collected data. This task finds a variety of applications including the off-policy evaluation (\textsf{OPE}) in contextual bandits, and estimation of the average treatment effect (\textsf{ATE}) in causal inference. While a certain class of augmented inverse propensity weighting (\textsf{AIPW}) estimators enjoys desirable asymptotic properties including the semi-parametric efficiency, much less is known about their non-asymptotic theory with adaptively collected data. To fill in the gap, we first establish generic upper bounds on the mean-squared error of the class of AIPW estimators that crucially depends on a sequentially weighted error between the treatment effect and its estimates. Motivated by this, we also propose a general reduction scheme that allows one to produce a sequence of estimates for the treatment effect via online learning to minimize the sequentially weighted estimation error. To illustrate this, we provide three concrete instantiations in (\romannumeral 1) the tabular case; (\romannumeral 2) the case of linear function approximation; and (\romannumeral 3) the case of general function approximation for the outcome model. We then provide a local minimax lower bound to show the instance-dependent optimality of the \textsf{AIPW} estimator using no-regret online learning algorithms.

Related papers

• C-Learner: Constrained Learning for Causal Inference and Semiparametric Statistics [5.395560682099634]
  We propose a novel debiased estimator that achieves stable plug-in estimates with desirable properties. Our constrained learning framework solves for the best plug-in estimator under the constraint that the first-order error with respect to the plugged-in quantity is zero. Our estimator outperforms one-step estimation and targeting in challenging settings with limited overlap between treatment and control, and performs comparably otherwise.
  arXiv  Detail & Related papers  (2024-05-15T16:38:28Z)
• Adaptive Linear Estimating Equations [5.985204759362746]
  In this paper, we propose a general method for constructing debiased estimator. It makes use of the idea of adaptive linear estimating equations, and we establish theoretical guarantees of normality. A salient feature of our estimator is that in the context of multi-armed bandits, our estimator retains the non-asymptotic performance.
  arXiv  Detail & Related papers  (2023-07-14T12:55:47Z)
• Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency [53.90687548731265]
  We study optimal procedures for estimating a linear functional based on observational data. For any convex and symmetric function class $mathcalF$, we derive a non-asymptotic local minimax bound on the mean-squared error.
  arXiv  Detail & Related papers  (2023-01-16T02:57:37Z)
• Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency [59.48096489854697]
  The problem of estimating a linear functional based on observational data is canonical in both the causal inference and bandit literatures. We prove non-asymptotic upper bounds on the mean-squared error of such procedures. We establish its instance-dependent optimality in finite samples via matching non-asymptotic local minimax lower bounds.
  arXiv  Detail & Related papers  (2022-09-26T23:50:55Z)
• Generalization bounds and algorithms for estimating conditional average treatment effect of dosage [13.867315751451494]
  We investigate the task of estimating the conditional average causal effect of treatment-dosage pairs from a combination of observational data and assumptions on the causal relationships in the underlying system. This has been a longstanding challenge for fields of study such as epidemiology or economics that require a treatment-dosage pair to make decisions. We show empirically new state-of-the-art performance results across several benchmark datasets for this problem.
  arXiv  Detail & Related papers  (2022-05-29T15:26:59Z)
• Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets [101.5329678997916]
  We study episodic two-player zero-sum Markov games (MGs) in the offline setting. The goal is to find an approximate Nash equilibrium (NE) policy pair based on a dataset collected a priori.
  arXiv  Detail & Related papers  (2022-02-15T15:39:30Z)
• Semi-Supervised Quantile Estimation: Robust and Efficient Inference in High Dimensional Settings [0.5735035463793009]
  We consider quantile estimation in a semi-supervised setting, characterized by two available data sets. We propose a family of semi-supervised estimators for the response quantile(s) based on the two data sets.
  arXiv  Detail & Related papers  (2022-01-25T10:02:23Z)
• Learning to Estimate Without Bias [57.82628598276623]
  Gauss theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models. In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance.
  arXiv  Detail & Related papers  (2021-10-24T10:23:51Z)
• Near-optimal inference in adaptive linear regression [60.08422051718195]
  Even simple methods like least squares can exhibit non-normal behavior when data is collected in an adaptive manner. We propose a family of online debiasing estimators to correct these distributional anomalies in at least squares estimation. We demonstrate the usefulness of our theory via applications to multi-armed bandit, autoregressive time series estimation, and active learning with exploration.
  arXiv  Detail & Related papers  (2021-07-05T21:05:11Z)
• Variance-Aware Off-Policy Evaluation with Linear Function Approximation [85.75516599931632]
  We study the off-policy evaluation problem in reinforcement learning with linear function approximation. We propose an algorithm, VA-OPE, which uses the estimated variance of the value function to reweight the Bellman residual in Fitted Q-Iteration.
  arXiv  Detail & Related papers  (2021-06-22T17:58:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.