Energy-Guided Continuous Entropic Barycenter Estimation for General Costs

• URL: http://arxiv.org/abs/2310.01105v3
• Date: Mon, 27 May 2024 09:24:19 GMT
• Title: Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
• Authors: Alexander Kolesov, Petr Mokrov, Igor Udovichenko, Milena Gazdieva, Gudmund Pammer, Anastasis Kratsios, Evgeny Burnaev, Alexander Korotin,
• Abstract summary: We propose a novel algorithm for approximating the continuous Entropic OT (EOT) barycenter for arbitrary OT cost functions. Our approach is built upon the dual reformulation of the EOT problem based on weak OT.
• Score: 95.33926437521046
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Optimal transport (OT) barycenters are a mathematically grounded way of averaging probability distributions while capturing their geometric properties. In short, the barycenter task is to take the average of a collection of probability distributions w.r.t. given OT discrepancies. We propose a novel algorithm for approximating the continuous Entropic OT (EOT) barycenter for arbitrary OT cost functions. Our approach is built upon the dual reformulation of the EOT problem based on weak OT, which has recently gained the attention of the ML community. Beyond its novelty, our method enjoys several advantageous properties: (i) we establish quality bounds for the recovered solution; (ii) this approach seamlessly interconnects with the Energy-Based Models (EBMs) learning procedure enabling the use of well-tuned algorithms for the problem of interest; (iii) it provides an intuitive optimization scheme avoiding min-max, reinforce and other intricate technical tricks. For validation, we consider several low-dimensional scenarios and image-space setups, including non-Euclidean cost functions. Furthermore, we investigate the practical task of learning the barycenter on an image manifold generated by a pretrained generative model, opening up new directions for real-world applications.

Related papers

• A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning [74.80956524812714]
  We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning. These problems are often formalized as Bi-Level optimizations (BLO) We introduce a novel perspective by turning a given BLO problem into a ii optimization, where the inner loss function becomes a smooth distribution, and the outer loss becomes an expected loss over the inner distribution.
  arXiv  Detail & Related papers  (2024-10-14T12:10:06Z)
• Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport [84.51977664336056]
  We propose a novel, scalable approach for estimating the textitrobust continuous barycenter. Our method is framed as a $min$-$max$ optimization problem and is adaptable to textitgeneral cost function.
  arXiv  Detail & Related papers  (2024-10-04T23:27:33Z)
• Global Convergence of Decentralized Retraction-Free Optimization on the Stiefel Manifold [12.414718831844041]
  We show that DRFGT performs retraction on a gradient based on the corresponding DRFGT method. Also show that DRFGT can be used to perform retraction on a network of agents.
  arXiv  Detail & Related papers  (2024-05-19T15:50:57Z)
• Estimating Barycenters of Distributions with Neural Optimal Transport [93.28746685008093]
  We propose a new scalable approach for solving the Wasserstein barycenter problem. Our methodology is based on the recent Neural OT solver. We also establish theoretical error bounds for our proposed approach.
  arXiv  Detail & Related papers  (2024-02-06T09:17:07Z)
• Entropic Neural Optimal Transport via Diffusion Processes [105.34822201378763]
  We propose a novel neural algorithm for the fundamental problem of computing the entropic optimal transport (EOT) plan between continuous probability distributions. Our algorithm is based on the saddle point reformulation of the dynamic version of EOT which is known as the Schr"odinger Bridge problem. In contrast to the prior methods for large-scale EOT, our algorithm is end-to-end and consists of a single learning step.
  arXiv  Detail & Related papers  (2022-11-02T14:35:13Z)
• Low-rank Optimal Transport: Approximation, Statistics and Debiasing [51.50788603386766]
  Low-rank optimal transport (LOT) approach advocated in citescetbon 2021lowrank LOT is seen as a legitimate contender to entropic regularization when compared on properties of interest. We target each of these areas in this paper in order to cement the impact of low-rank approaches in computational OT.
  arXiv  Detail & Related papers  (2022-05-24T20:51:37Z)

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.