LGOct 4, 2023

Optimal Transport with Adaptive Regularisation

arXiv:2310.02925v12 citationsh-index: 35
Originality Incremental advance
AI Analysis

This work addresses a specific issue in optimal transport for domain adaptation, representing an incremental improvement.

The paper tackled the problem of mass imbalance in regularized optimal transport by introducing OTARI, a formulation with adaptive constraints per point, and demonstrated its benefits for domain adaptation.

Regularising the primal formulation of optimal transport (OT) with a strictly convex term leads to enhanced numerical complexity and a denser transport plan. Many formulations impose a global constraint on the transport plan, for instance by relying on entropic regularisation. As it is more expensive to diffuse mass for outlier points compared to central ones, this typically results in a significant imbalance in the way mass is spread across the points. This can be detrimental for some applications where a minimum of smoothing is required per point. To remedy this, we introduce OT with Adaptive RegularIsation (OTARI), a new formulation of OT that imposes constraints on the mass going in or/and out of each point. We then showcase the benefits of this approach for domain adaptation.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes