Establishes finite-sample regret bounds of order sqrt(N-dim(Π)/N) for IPW and DR estimators in Wasserstein policy learning with distributional outcomes, plus a matching minimax lower bound.
Accountability and flexibility in public schools: Evidence from Boston’s charters and pilots
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Local disclosure via post-hoc explanations enables consistent doubly robust estimation of policy value in one-shot OPE with strategic agents by recovering pre-strategic covariates under a conditional log-normal cost sensitivity assumption.
NBPL uses a nonparametric Dirichlet process prior on the reduced-form distribution for posterior inference on optimal treatment assignments and welfare, with minimax-optimal regret convergence and pointwise consistent policy class comparisons.
citing papers explorer
-
Wasserstein Policy Learning for Distributional Outcomes
Establishes finite-sample regret bounds of order sqrt(N-dim(Π)/N) for IPW and DR estimators in Wasserstein policy learning with distributional outcomes, plus a matching minimax lower bound.
-
Off-Policy Evaluation with Strategic Agents via Local Disclosure
Local disclosure via post-hoc explanations enables consistent doubly robust estimation of policy value in one-shot OPE with strategic agents by recovering pre-strategic covariates under a conditional log-normal cost sensitivity assumption.
-
Nonparametric Bayesian Policy Learning
NBPL uses a nonparametric Dirichlet process prior on the reduced-form distribution for posterior inference on optimal treatment assignments and welfare, with minimax-optimal regret convergence and pointwise consistent policy class comparisons.