Meta Optimal Transport
read the original abstract
We study the use of amortized optimization to predict optimal transport (OT) maps from the input measures, which we call Meta OT. This helps repeatedly solve similar OT problems between different measures by leveraging the knowledge and information present from past problems to rapidly predict and solve new problems. Otherwise, standard methods ignore the knowledge of the past solutions and suboptimally re-solve each problem from scratch. We instantiate Meta OT models in discrete and continuous settings between grayscale images, spherical data, classification labels, and color palettes and use them to improve the computational time of standard OT solvers. Our source code is available at http://github.com/facebookresearch/meta-ot
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Self-organized robustness in mean-field interacting systems
A tractable mean-field model casts self-organized robustness as meta-optimization, producing a self-consistent seascape whose shape accelerates relaxation via optimized Wasserstein gradient flow and preferentially enc...
-
Measure-to-measure Regression with Transformers
Formalizes nonlinear M2M regression and introduces transformer architectures as static maps and dynamic velocity fields between probability measures, tested on synthetic, particle, and organoid datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.