Forward Tangent-Centered Sinkhorn DRO: Exact Nominal Recovery from Optimal Transport to KL
Abstract
Fixed-reference entropy-regularized transport yields smooth distributionally robust optimization (DRO) objectives, but its value as a function of the adversarial marginal is generally minimized at a kernel-smoothed law rather than at the nominal distribution. Consequently, the smallest raw ambiguity set need not recover nominal risk. Building on prior information-geometric plan-KL orientations, we study the forward tangent-centered discrepancy obtained by subtracting the value and first variation at the nominal law. This is the unique affine recentering, up to the simplex gauge; for symmetric costs, its plan-KL representation coincides with the forward candidate noted by Amari et al. (2018). The representation shows that the discrepancy dominates marginal KL, is uniquely zero at the nominal law, and is strongly convex in total variation. The resulting DRO problem retains a scalar log-sum-exp dual and closed-form conditional adversarial weights. On finite supports with symmetric zero-diagonal costs, the discrepancy converges uniformly to the unregularized transport cost at low temperature; for any finite cost, its rescaled value converges uniformly to marginal KL at high temperature. We derive its exact local Hessian, an explicit finite-sample containment radius, and a generalized chi-square calibration for multinomial data. Controlled simulations verify nominal centering, both limiting regimes, and practical plug-in coverage.
Related
- Accelerating Sinkhorn for Entropy-Regularized Optimal Transport
- Exponential convergence of Sinkhorn algorithm for entropy martingale optimal transport
- Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport
- Annealed Sinkhorn with Momentum: Certified Unregularized Optimal Transport in Linear Memory
- Relevance Propagation as Entropic Optimal Transport on Filippov Neural Networks: Sinkhorn Propagation and Region Relevance in Image Classifiers
BibTeX
@misc{guo2026forward,
title = {{Forward Tangent-Centered Sinkhorn DRO: Exact Nominal Recovery from Optimal Transport to KL}},
author = {Junjie Guo},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.30144},
eprint = {2610.30144},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.30144},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Forward Tangent-Centered Sinkhorn DRO: Exact Nominal Recovery from Optimal Transport to KL
AU - Junjie Guo
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.30144
UR - https://arxiv.org/abs/2610.30144
AB - Fixed-reference entropy-regularized transport yields smooth distributionally robust optimization (DRO) objectives, but its value as a function of the adversarial marginal is generally minimized at a kernel-smoothed law rather than at the nominal distribution. Consequently, the smallest raw ambiguity set need not recover nominal risk. Building on prior information-geometric plan-KL orientations, we study the forward tangent-centered discrepancy obtained by subtracting the value and first variation at the nominal law. This is the unique affine recentering, up to the simplex gauge; for symmetric costs, its plan-KL representation coincides with the forward candidate noted by Amari et al. (2018). The representation shows that the discrepancy dominates marginal KL, is uniquely zero at the nominal law, and is strongly convex in total variation. The resulting DRO problem retains a scalar log-sum-exp dual and closed-form conditional adversarial weights. On finite supports with symmetric zero-diagonal costs, the discrepancy converges uniformly to the unregularized transport cost at low temperature; for any finite cost, its rescaled value converges uniformly to marginal KL at high temperature. We derive its exact local Hessian, an explicit finite-sample containment radius, and a generalized chi-square calibration for multinomial data. Controlled simulations verify nominal centering, both limiting regimes, and practical plug-in coverage.
ER -