Empirical Optimal Transport between Conditional Distributions

by   Piyushi Manupriya, et al.

Given samples from two joint distributions, we consider the problem of Optimal Transportation (OT) between the corresponding distributions conditioned on a common variable. The objective of this work is to estimate the associated transport cost (Wasserstein distance) as well as the transport plan between the conditionals as a function of the conditioned value. Since matching conditional distributions is at the core of supervised training of discriminative models and (implicit) conditional-generative models, OT between conditionals has the potential to be employed in diverse machine learning applications. However, since the conditionals involved in OT are implicitly specified via the joint samples, it is challenging to formulate this problem, especially when (i) the variable conditioned on is continuous and (ii) the marginal of this variable in the two distributions is different. We overcome these challenges by employing a specific kernel MMD (Maximum Mean Discrepancy) based regularizer that ensures the marginals of our conditional transport plan are close to the conditionals specified via the given joint samples. Under mild conditions, we prove that our estimator for this regularized transport cost is statistically consistent and derive finite-sample bounds on the estimation error. Application-specific details for parameterizing our conditional transport plan are also presented. Furthermore, we empirically evaluate our methodology on benchmark datasets in applications like classification, prompt learning for few-shot classification, and conditional-generation in the context of predicting cell responses to cancer treatment.


page 14

page 15


A Consistent Extension of Discrete Optimal Transport Maps for Machine Learning Applications

Optimal transport maps define a one-to-one correspondence between probab...

Wasserstein Geodesic Generator for Conditional Distributions

Generating samples given a specific label requires estimating conditiona...

Entropy-regularized Optimal Transport Generative Models

We investigate the use of entropy-regularized optimal transport (EOT) co...

Large-Scale Optimal Transport and Mapping Estimation

This paper presents a novel two-step approach for the fundamental proble...

Regularized Finite Dimensional Kernel Sobolev Discrepancy

We show in this note that the Sobolev Discrepancy introduced in Mroueh e...

Comparing Probability Distributions with Conditional Transport

To measure the difference between two probability distributions, we prop...

Supervised Training of Conditional Monge Maps

Optimal transport (OT) theory describes general principles to define and...

Please sign up or login with your details

Forgot password? Click here to reset