paper-with-me

Papers

Sinkhorn Algorithm as a Special Case of Stochastic Mirror Descent

2019-09-16 · Konstantin Mishchenko

We present a new perspective on the celebrated Sinkhorn algorithm by showing that is a special case of incremental/stochastic mirror descent. In order to see this, one should simply plug Kullback-Leibler divergence in both mirror map and the objective function. Since the problem has unbounded domain, the objective function is neither smooth nor it has bounded gradients. However, one can still approach the problem using the notion of relative smoothness, obtaining that the stochastic objective is 1-relative smooth. The discovered equivalence allows us to propose 1) new methods for optimal transport, 2) an extension of Sinkhorn algorithm beyond two constraints.

📄 PDF Abstract BibTeX arXiv:1909.06918

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Wasserstein Mirror Gradient Flow as the limit of the Sinkhorn Algorithm

2023-07-31 · Nabarun Deb, Young-Heon Kim, Soumik Pal, Geoffrey Schiebinger

We prove that the sequence of marginals obtained from the iterations of the Sinkhorn algorithm or the iterative proportional fitting procedure (IPFP) on joint densities, converges to an absolutely continuous curve on the…

Improved Rate of First Order Algorithms for Entropic Optimal Transport

2023-01-23 · Yiling Luo, Yiling Xie, Xiaoming Huo

This paper improves the state-of-the-art rate of a first-order algorithm for solving entropy regularized optimal transport. The resulting rate for approximating the optimal transport (OT) has been improved from $\widetil…

Sinkhorn Distributionally Robust Optimization

2021-09-24 · Jie Wang, Rui Gao, Yao Xie

We study distributionally robust optimization with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributi…

Sinkhorn Flow: A Continuous-Time Framework for Understanding and Generalizing the Sinkhorn Algorithm

2023-11-28 · Mohammad Reza Karimi, Ya-Ping Hsieh, Andreas Krause

Many problems in machine learning can be formulated as solving entropy-regularized optimal transport on the space of probability measures. The canonical approach involves the Sinkhorn iterates, renowned for their rich ma…

Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes

2022-11-18 · Marin Ballu, Quentin Berthet

Optimal transport is an important tool in machine learning, allowing to capture geometric properties of the data through a linear program on transport polytopes. We present a single-loop optimization algorithm for minimi…

Point Cloud Registration