Pith. sign in

REVIEW 1 cited by

Beyond entropic regularization: Debiased Gaussian estimators for discrete optimal transport and general linear programs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.04312 v1 pith:MAL7SXY5 submitted 2025-05-07 math.ST stat.TH

classification math.STstat.TH
keywords linearoptimalestimatorspenalizationregularizationtransportapproachasymptotically
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This work proposes new estimators for discrete optimal transport plans that enjoy Gaussian limits centered at the true solution. This behavior stands in stark contrast with the performance of existing estimators, including those based on entropic regularization, which are asymptotically biased and only satisfy a CLT centered at a regularized version of the population-level plan. We develop a new regularization approach based on a different class of penalty functions, which can be viewed as the duals of those previously considered in the literature. The key feature of these penalty schemes it that they give rise to preliminary estimates that are asymptotically linear in the penalization strength. Our final estimator is obtained by constructing an appropriate linear combination of two penalized solutions corresponding to two different tuning parameters so that the bias introduced by the penalization cancels out. Unlike classical debiasing procedures, therefore, our proposal entirely avoids the delicate problem of estimating and then subtracting the estimated bias term. Our proofs, which apply beyond the case of optimal transport, are based on a novel asymptotic analysis of penalization schemes for linear programs. As a corollary of our results, we obtain the consistency of the naive bootstrap for fully data-driven inference on the true optimal solution. Simulation results and two data analyses support strongly the benefits of our approach relative to existing techniques.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Partial identification via conditional linear programs: estimation and policy learning

    stat.ME 2025-06 conditional novelty 7.0 of 10

    Two debiased estimators, one based on linear programming solutions and one on entropic smoothing, provide asymptotic confidence intervals for covariate-dependent partial identification bounds and support policy learning.

Pith tools