Timezone: »

Meta Optimal Transport
Brandon Amos · Giulia Luise · samuel cohen · Ievgen Redko

Thu Jul 27 04:30 PM -- 06:00 PM (PDT) @ Exhibit Hall 1 #110

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

Author Information

Brandon Amos (Meta)
Giulia Luise (Microsoft Research)
samuel cohen (University College London)
Ievgen Redko (Huawei Technologies SASU France 18 Quai du point du jour, 92100 Boulogne-Billancourt,)

More from the Same Authors