XVII th Conference on Stochastic Programming

Federated Calculation of the Transportation Barycenter by Dual Decomposition

Non programmé

30m

F206

Invited talk Machine learning ML

Orateur

Zhengqi Lin

Description

We propose an efficient federated dual decomposition algorithm for calculating the
Wasserstein barycenter of several distributions. The algorithm does not have
access to local data and uses only highly aggregate information. Owing to the
absence of any matrix-vector operations, the algorithm exhibits very low complexity of
each iteration and significant scalability. We illustrate its virtues on several examples of
mixture models.