An Homogeneous Unbalanced Regularized Optimal Transport model with applications to Optimal Transport with Boundary

• URL: http://arxiv.org/abs/2201.02082v1
• Date: Thu, 6 Jan 2022 14:55:30 GMT
• Title: An Homogeneous Unbalanced Regularized Optimal Transport model with applications to Optimal Transport with Boundary
• Authors: Th\'eo Lacombe
• Abstract summary: We show how the introduction of the entropic regularization term in unbalanced Optimal Transport (OT) models may alter their homogeneity with respect to the input measures. We propose to modify the entropic regularization term to retrieve an UROT model that is homogeneous while preserving most properties of the standard UROT model.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work studies how the introduction of the entropic regularization term in unbalanced Optimal Transport (OT) models may alter their homogeneity with respect to the input measures. We observe that in common settings (including balanced OT and unbalanced OT with Kullback-Leibler divergence to the marginals), although the optimal transport cost itself is not homogeneous, optimal transport plans and the so-called Sinkhorn divergences are indeed homogeneous. However, homogeneity does not hold in more general Unbalanced Regularized Optimal Transport (UROT) models, for instance those using the Total Variation as divergence to the marginals. We propose to modify the entropic regularization term to retrieve an UROT model that is homogeneous while preserving most properties of the standard UROT model. We showcase the importance of using our Homogeneous UROT (HUROT) model when it comes to regularize Optimal Transport with Boundary, a transportation model involving a spatially varying divergence to the marginals for which the standard (inhomogeneous) UROT model would yield inappropriate behavior.

Related papers

• Optimal spectral transport of non-Hermitian systems [3.4031290796757436]
  We study the optimal transport of the eigenspectrum of one-dimensional non-Hermitian models as the spectrum deforms on the complex plane under a varying imaginary gauge field. Characterizing the optimal spectral transport through the Wasserstein metric, we show that, indeed, important features of the non-Hermitian model can be determined. Our work highlights the key role of spectral geometry in non-Hermitian physics, and offers a practical and convenient access to the properties of non-Hermitian models.
  arXiv  Detail & Related papers  (2025-01-25T13:23:53Z)
• A note on the relations between mixture models, maximum-likelihood and entropic optimal transport [6.246185995463311]
  We show that performing maximum-likelihood estimation for a mixture model is equivalent to minimizing over the parameters an optimal transport problem with entropic regularization.
  arXiv  Detail & Related papers  (2025-01-21T09:55:21Z)
• Equivariant Flow Matching with Hybrid Probability Transport [69.11915545210393]
  Diffusion Models (DMs) have demonstrated effectiveness in generating feature-rich geometries. DMs typically suffer from unstable probability dynamics with inefficient sampling speed. We introduce geometric flow matching, which enjoys the advantages of both equivariant modeling and stabilized probability dynamics.
  arXiv  Detail & Related papers  (2023-12-12T11:13:13Z)
• Convergence Rates for Regularized Optimal Transport via Quantization [3.04585143845864]
  We study the convergence of divergence-regularized optimal transport as the regularization parameter vanishes. A novel methodology using quantization and martingale couplings is suitable for non-compact marginals.
  arXiv  Detail & Related papers  (2022-08-30T16:58:40Z)
• Super-model ecosystem: A domain-adaptation perspective [101.76769818069072]
  This paper attempts to establish the theoretical foundation for the emerging super-model paradigm via domain adaptation. Super-model paradigms help reduce computational and data cost and carbon emission, which is critical to AI industry.
  arXiv  Detail & Related papers  (2022-08-30T09:09:43Z)
• Manifold Interpolating Optimal-Transport Flows for Trajectory Inference [64.94020639760026]
  We present a method called Manifold Interpolating Optimal-Transport Flow (MIOFlow) MIOFlow learns, continuous population dynamics from static snapshot samples taken at sporadic timepoints. We evaluate our method on simulated data with bifurcations and merges, as well as scRNA-seq data from embryoid body differentiation, and acute myeloid leukemia treatment.
  arXiv  Detail & Related papers  (2022-06-29T22:19:03Z)
• An Optimal Transport Formulation of Bayes' Law for Nonlinear Filtering Algorithms [7.919213739992465]
  This paper presents a variational representation of the Bayes' law using optimal transportation theory. By imposing certain structure on the transport map, the solution to the variational problem is used to construct a Brenier-type map. The proposed methodology is used to derive the optimal transport form of the feedback particle filler (FPF) in the continuous-time limit.
  arXiv  Detail & Related papers  (2022-03-22T16:43:33Z)
• Simultaneous Transport Evolution for Minimax Equilibria on Measures [48.82838283786807]
  Min-max optimization problems arise in several key machine learning setups, including adversarial learning and generative modeling. In this work we focus instead in finding mixed equilibria, and consider the associated lifted problem in the space of probability measures. By adding entropic regularization, our main result establishes global convergence towards the global equilibrium.
  arXiv  Detail & Related papers  (2022-02-14T02:23:16Z)
• Nearly Tight Convergence Bounds for Semi-discrete Entropic Optimal Transport [0.483420384410068]
  We derive nearly tight and non-asymptotic convergence bounds for solutions of entropic semi-discrete optimal transport. Our results also entail a non-asymptotic and tight expansion of the difference between the entropic and the unregularized costs.
  arXiv  Detail & Related papers  (2021-10-25T06:52:45Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• Comparing Probability Distributions with Conditional Transport [63.11403041984197]
  We propose conditional transport (CT) as a new divergence and approximate it with the amortized CT (ACT) cost. ACT amortizes the computation of its conditional transport plans and comes with unbiased sample gradients that are straightforward to compute. On a wide variety of benchmark datasets generative modeling, substituting the default statistical distance of an existing generative adversarial network with ACT is shown to consistently improve the performance.
  arXiv  Detail & Related papers  (2020-12-28T05:14:22Z)

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.