Skip to yearly menu bar Skip to main content


Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes

Marin Ballu · Quentin Berthet

Exhibit Hall 1 #131
[ ]
[ Slides [ PDF


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 minimizing general convex objectives on these domains, utilizing the principles of Sinkhorn matrix scaling and mirror descent. The proposed algorithm is robust to noise, and can be used in an online setting. We provide theoretical guarantees for convex objectives and experimental results showcasing it effectiveness on both synthetic and real-world data.

Chat is not available.