Score: 1
Deriving the Gradients of Some Popular Optimal Transport Algorithms
Published: April 11, 2025 |
arXiv ID: 2504.08722v1
By: Fangzhou Xie
Potential Business Impact:
Helps computers find the best way to move things.
Business Areas:
Autonomous Vehicles
Transportation
In this note, I review entropy-regularized Monge-Kantorovich problem in Optimal Transport, and derive the gradients of several popular algorithms popular in Computational Optimal Transport, including the Sinkhorn algorithms, Wasserstein Barycenter algorithms, and the Wasserstein Dictionary Learning algorithms.
Similar Papers
88%
Optimal Transport for Machine Learners
Machine Learning (Stat)
Helps computers learn by comparing data.
10 May 2025
0
87%
Dual Block Gradient Ascent for Entropically Regularised Quantum Optimal Transport
Mathematical Physics
Solves hard math problems for quantum computers.
22 Mar 2025
0
87%
An Optimal Transport approach to arbitrage correction: Application to volatility Stress-Tests
Mathematical Finance
Fixes unfair money chances in stock prices.
21 Jan 2025
1
Repos / Data Links
Page Count
43 pages
Category
Mathematics:
Optimization and Control