Timezone: »
Inverse Optimal Transport (IOT) studies the problem of inferring the underlying cost that gives rise to an observation on coupling two probability measures. Couplings appear as the outcome of matching sets (e.g. dating) and moving distributions (e.g. transportation). Compared to Optimal transport (OT), the mathematical theory of IOT is undeveloped. We formalize and systematically analyze the properties of IOT using tools from the study of entropy-regularized OT. Theoretical contributions include characterization of the manifold of cross-ratio equivalent costs, the implications of model priors, and derivation of an MCMC sampler. Empirical contributions include visualizations of cross-ratio equivalent effect on basic examples, simulations validating theoretical results and experiments on real world data.
Author Information
Wei-Ting Chiu (Rutgers University - Newark)
Pei Wang (Rutgers University-Newark)
Patrick Shafto (IAS / Rutgers University)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Poster: Discrete Probabilistic Inverse Optimal Transport »
Wed. Jul 20th through Thu the 21st Room Hall E #703
More from the Same Authors
-
2023 : On feasibility of intent obfuscating attacks »
ZhaoBin Li · Patrick Shafto -
2023 Poster: Coupled Variational Autoencoder »
Xiaoran Hao · Patrick Shafto -
2022 Poster: A Psychological Theory of Explainability »
Scott Cheng-Hsin Yang · Nils Erik Tomas Folke · Patrick Shafto -
2022 Spotlight: A Psychological Theory of Explainability »
Scott Cheng-Hsin Yang · Nils Erik Tomas Folke · Patrick Shafto -
2021 Poster: Interactive Learning from Activity Description »
Khanh Nguyen · Dipendra Misra · Robert Schapire · Miroslav Dudik · Patrick Shafto -
2021 Spotlight: Interactive Learning from Activity Description »
Khanh Nguyen · Dipendra Misra · Robert Schapire · Miroslav Dudik · Patrick Shafto -
2020 Poster: Sequential Cooperative Bayesian Inference »
Junqi Wang · Pei Wang · Patrick Shafto