PulseAugur
EN
LIVE 12:10:33

New optimal transport methods offer improved accuracy and scalability

By PulseAugur Editorial · [5 sources] ·

Researchers have introduced Sliced-Regularized Optimal Transport (SROT), a novel formulation that regularizes transport plans towards a smoothed sliced OT plan, offering more accurate approximations than entropic OT. A new Sinkhorn-style algorithm enables efficient computation, maintaining scalability. Experiments on synthetic data and color transfer tasks demonstrate SROT's superiority over existing methods in approximating exact OT plans and its utility in gradient flow analysis. AI

IMPACT Introduces improved methods for optimal transport, potentially enhancing downstream applications in machine learning and data analysis.

RANK_REASON The cluster contains two arXiv papers introducing new methods for optimal transport.

Read on arXiv stat.ML →

AI-generated summary · Google Gemini · from 5 sources. How we write summaries →

New optimal transport methods offer improved accuracy and scalability

COVERAGE [5]

  1. arXiv stat.ML TIER_1 English(EN) · Khai Nguyen ·

    Sliced-Regularized Optimal Transport

    arXiv:2604.23944v1 Announce Type: new Abstract: We propose a new regularized optimal transport (OT) formulation, termed sliced-regularized optimal transport (SROT). Unlike entropic OT (EOT), which regularizes the transport plan toward an independent coupling, SROT regularizes it …

  2. arXiv stat.ML TIER_1 English(EN) · Yumiharu Nakano ·

    Continuum-marginal optimal transport: a mesh-free kernel method

    arXiv:2604.24226v1 Announce Type: cross Abstract: In this paper we study continuum-marginal optimal transport. Given a time-continuous family of probability marginals, the problem is to recover the minimum-energy velocity field whose flow reproduces every marginal. This problem i…

  3. arXiv stat.ML TIER_1 English(EN) · Yumiharu Nakano ·

    Continuum-marginal optimal transport: a mesh-free kernel method

    In this paper we study continuum-marginal optimal transport. Given a time-continuous family of probability marginals, the problem is to recover the minimum-energy velocity field whose flow reproduces every marginal. This problem is the continuum limit of the classical two-margina…

  4. arXiv stat.ML TIER_1 English(EN) · Khai Nguyen ·

    Sliced-Regularized Optimal Transport

    We propose a new regularized optimal transport (OT) formulation, termed sliced-regularized optimal transport (SROT). Unlike entropic OT (EOT), which regularizes the transport plan toward an independent coupling, SROT regularizes it toward a smoothened sliced OT (SOT) plan. To the…

  5. arXiv stat.ML TIER_1 English(EN) · Khai Nguyen ·

    Sliced-Regularized Optimal Transport

    We propose a new regularized optimal transport (OT) formulation, termed sliced-regularized optimal transport (SROT). Unlike entropic OT (EOT), which regularizes the transport plan toward an independent coupling, SROT regularizes it toward a smoothened sliced OT (SOT) plan. To the…

RELATED ENTITIES

RELATED TOPICS