Department of Mathematics, Columbia University(哥伦比亚大学数学系);HKU Musketeers Foundation Institute of Data Science(香港大学 Musketeers 基金会数据科学研究所);HKU-Shanghai Intelligent Computing Research Center(香港大学-上海智能计算研究中心)
Optimal transport (OT) aims to find a map $T$ that transports mass from one probability measure to another while minimizing a cost function. Recently, neural OT solvers have gained popularity in high dimensional biological applications such as drug perturbation, due to their superior computational and memory efficiency compared to traditional exact Sinkhorn solvers. However, the overly complex high dimensional maps learned by neural OT solvers often suffer from poor interpretability. Prior work addressed this issue in the context of exact OT solvers by introducing \emph{displacement-sparse maps} via designed elastic cost, but such method failed to be applied to neural OT settings. In this work, we propose an intuitive and theoretically grounded approach to learning \emph{displacement-sparse maps} within neural OT solvers. Building on our new formulation, we introduce a novel smoothed $\ell_0$ regularizer that outperforms the $\ell_1$ based alternative from prior work. Leveraging Input Convex Neural Network's flexibility, we further develop a heuristic framework for adaptively controlling sparsity intensity, an approach uniquely enabled by the neural OT paradigm. We demonstrate the necessity of this adaptive framework in large-scale, high-dimensional training, showing not only improved accuracy but also practical ease of use for downstream applications.
Accelerated Algorithm for Sparse Regularized Partial Optimal Transport
Hanoi University of Science and Technology(河内理工大学);High School for the Gifted(天才高中);VinUniversity;Rochambeau French International School(罗尚博法语国际学校);RMIT University(皇家墨尔本理工大学);Aalto University(阿尔托大学);Linköping University(林雪平大学)
Online Learning to Transport via the Minimal Selection Principle
University of Chicago(芝加哥大学);University of British Columbia(不列颠哥伦比亚大学)
基于运筹学中的鲁棒动态资源分配问题,本文研究了决策变量为概率测度的无穷维对象的\textit{Online Learning to Transport}(OLT)问题。我们通过一种称为最小选择原理的见解,在在线学习、最优运输和偏微分方程之间建立联系,该原理最初由\citet{Ambrosio_2005}在Wasserstein梯度流设置中研究。这使我们能够将标准的在线学习框架无缝地扩展到无限维环境。基于我们的框架,我们推导出一种新的方法,称为\textit{minimal selection or exploration (MSoE) algorithm}解决OLT问题,使用平均场近似和离散化技术。在位移凸设置,支撑我们的方法的主要理论信息是,随着时间的推移,最小化运输成本(通过最小选择原则),确保最佳的累积遗憾上限。在算法方面,我们的MSoE算法适用于位移凸设置之外,使得最优传输的数学理论实际上与动态资源分配中常见的非凸设置相关。
Learning effective Sargassum transport dynamics from limited drifter observations
Rosenstiel School of Marine, Atmospheric, and Earth Science(罗森斯蒂尔海洋、大气与地球科学学院);University of Miami(迈阿密大学);Department of Atmospheric Sciences(大气科学系);Department of Ocean Sciences(海洋科学系);Department of Marine Sciences(海洋科学系);University of Puerto Rico(波多黎各大学)