Abstract:The goal of optimal transport (OT) is to find optimal assignments or matchings between data sets which minimize the total cost for a given cost function. However, sometimes the cost function is unknown but we have access to (parts of) the solution to the OT problem, e.g.\ the OT plan or the value of the objective function. Recovering the cost from such information is called inverse OT and has become recently of certain interest triggered by novel applications, e.g.\ in social science and economics. This raises the issue under which circumstances such cost is identifiable, i.e., it can be uniquely recovered from other OT quantities. In this work we provide sufficient and necessary conditions for the identifiability of the cost function on finite ground spaces. We find that such conditions correspond to the combinatorial structure of the corresponding linear program and discuss its computational complexity and implications for cost estimation in statistical linear models.
From: Michel Groppe [view email]
[v1]
Wed, 30 Oct 2024 16:03:13 UTC (49 KB)
[v2]
Mon, 1 Sep 2025 08:26:13 UTC (50 KB)
[v3]
Wed, 27 May 2026 08:33:20 UTC (60 KB)
[v4]
Thu, 6 Aug 2026 07:19:53 UTC (61 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。