Neural Optimal Transport with General Cost Functionals

• URL: http://arxiv.org/abs/2205.15403v4
• Date: Thu, 30 May 2024 15:11:45 GMT
• Title: Neural Optimal Transport with General Cost Functionals
• Authors: Arip Asadulaev, Alexander Korotin, Vage Egiazarian, Petr Mokrov, Evgeny Burnaev,
• Abstract summary: We introduce a novel neural network-based algorithm to compute optimal transport plans for general cost functionals. As an application, we construct a cost functional to map data distributions while preserving the class-wise structure.
• Score: 66.41953045707172
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a novel neural network-based algorithm to compute optimal transport (OT) plans for general cost functionals. In contrast to common Euclidean costs, i.e., $\ell^1$ or $\ell^2$, such functionals provide more flexibility and allow using auxiliary information, such as class labels, to construct the required transport map. Existing methods for general costs are discrete and have limitations in practice, i.e. they do not provide an out-of-sample estimation. We address the challenge of designing a continuous OT approach for general costs that generalizes to new data points in high-dimensional spaces, such as images. Additionally, we provide the theoretical error analysis for our recovered transport plans. As an application, we construct a cost functional to map data distributions while preserving the class-wise structure.

Related papers

• Fast and scalable Wasserstein-1 neural optimal transport solver for single-cell perturbation prediction [55.89763969583124]
  Optimal transport theory provides a principled framework for constructing such mappings. We propose a novel optimal transport solver based on Wasserstein-1. Our experiments demonstrate that the proposed solver can mimic the $W$ OT solvers in finding a unique and monotonic" map on 2D datasets.
  arXiv  Detail & Related papers  (2024-11-01T14:23:19Z)
• Differentiable Cost-Parameterized Monge Map Estimators [19.015367254988448]
  It is desirable to use known information to tailor cost functions and hence learn OT maps which are adapted to the problem at hand. We construct a differentiable Monge map estimator which can be optimized to be consistent with known information about an OT map. Our method provides a general approach for incorporating prior information about the Monge map itself when learning adapted OT maps and cost functions.
  arXiv  Detail & Related papers  (2024-06-12T16:47:54Z)
• Quantum Theory and Application of Contextual Optimal Transport [2.160404814399144]
  We propose a first-of-its-kind quantum computing formulation for amortized optimization of contextualized transportation plans. We report a performance that cannot be matched with our classical neural OT approach.
  arXiv  Detail & Related papers  (2024-02-22T22:03:16Z)
• Normalizing flows as approximations of optimal transport maps via linear-control neural ODEs [49.1574468325115]
  "Normalizing Flows" is related to the task of constructing invertible transport maps between probability measures by means of deep neural networks. We consider the problem of recovering the $Wamma$-optimal transport map $T$ between absolutely continuous measures $mu,nuinmathcalP(mathbbRn)$ as the flow of a linear-control neural ODE.
  arXiv  Detail & Related papers  (2023-11-02T17:17:03Z)
• A Specialized Semismooth Newton Method for Kernel-Based Optimal Transport [92.96250725599958]
  Kernel-based optimal transport (OT) estimators offer an alternative, functional estimation procedure to address OT problems from samples. We show that our SSN method achieves a global convergence rate of $O (1/sqrtk)$, and a local quadratic convergence rate under standard regularity conditions.
  arXiv  Detail & Related papers  (2023-10-21T18:48:45Z)
• Optimal transport map estimation in general function spaces [17.323588442718926]
  We study the problem of estimating a function $T$ given independent samples from a distribution $P$ and from the pushforward distribution $T_sharp P$. This setting is motivated by applications in the sciences, where $T$ represents the evolution of a physical system over time. We present a unified methodology for obtaining rates of estimation of optimal transport maps in general function spaces.
  arXiv  Detail & Related papers  (2022-12-07T15:42:11Z)
• InfoOT: Information Maximizing Optimal Transport [58.72713603244467]
  InfoOT is an information-theoretic extension of optimal transport. It maximizes the mutual information between domains while minimizing geometric distances. This formulation yields a new projection method that is robust to outliers and generalizes to unseen samples.
  arXiv  Detail & Related papers  (2022-10-06T18:55:41Z)
• Measuring Generalization with Optimal Transport [111.29415509046886]
  We develop margin-based generalization bounds, where the margins are normalized with optimal transport costs. Our bounds robustly predict the generalization error, given training data and network parameters, on large scale datasets.
  arXiv  Detail & Related papers  (2021-06-07T03:04:59Z)
• Bayesian Inference for Optimal Transport with Stochastic Cost [22.600086666266243]
  In machine learning and computer vision, optimal transport has had significant success in learning generative models. We introduce a framework for inferring the optimal transport plan distribution by induced cost. We also tailor an HMC method to sample from the resulting transport plan distribution.
  arXiv  Detail & Related papers  (2020-10-19T09:07:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.