Fitted occupancy-ratio evaluation (FORE) contracts in KL divergence under only occupancy-ratio realizability, enabling offline policy evaluation without Bellman completeness.
Source Condition Double Robust Inference on Functionals of Inverse Problems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
We consider estimation of parameters defined as linear functionals of solutions to linear inverse problems. Any such parameter admits a doubly robust representation that depends on the solution to a dual linear inverse problem, where the dual solution can be thought as a generalization of the inverse propensity function. We provide the first source condition double robust inference method that ensures asymptotic normality around the parameter of interest as long as either the primal or the dual inverse problem is sufficiently well-posed, without knowledge of which inverse problem is the more well-posed one. Our result is enabled by novel guarantees for iterated Tikhonov regularized adversarial estimators for linear inverse problems, over general hypothesis spaces, which are developments of independent interest.
years
2026 2representative citing papers
A single-regularization-parameter RKHS estimator for average marginal effects in partially linear IV models is shown to be consistent and asymptotically normal, with a valid Bayesian bootstrap for inference.
citing papers explorer
-
Fitted Occupancy-Ratio Evaluation without Bellman Completeness
Fitted occupancy-ratio evaluation (FORE) contracts in KL divergence under only occupancy-ratio realizability, enabling offline policy evaluation without Bellman completeness.
-
Average Marginal Effects in One-Step Partially Linear Instrumental Regressions
A single-regularization-parameter RKHS estimator for average marginal effects in partially linear IV models is shown to be consistent and asymptotically normal, with a valid Bayesian bootstrap for inference.