A Provably Convergent and Practical Algorithm for Gromov--Wasserstein Optimal Transport
cs.LG, math.OC
Submitted: 2026-05-05
Updated: 2026-10-28
Comments: 21 Pages, 6 figures
Project page: https://pythonot.github.io/auto_examples/index.html
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Accelerating Multi-Block Constrained Optimization Through Learning to Optimize
- PDOT: a Practical Primal-Dual Algorithm and a GPU-Based Solver for Optimal Transport
- PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport
- ripALM: A Relative-Type Inexact Proximal Augmented Lagrangian Method for Linearly Constrained Convex Optimization
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis