Nhat Ho

Improving Mini-batch Optimal Transport via Partial Transportation

2021 · arXiv (Cornell University)

Mini-batch optimal transport (m-OT) has been widely used recently to deal with the memory issue of OT in large-scale applications. Despite their practicality, m-OT suffers from misspecified mappings, namely, mappings that are optimal on the …

Architecture Agnostic Federated Learning for Neural Networks

2022 · arXiv (Cornell University)

With growing concerns regarding data privacy and rapid increase in data volume, Federated Learning(FL) has become an important learning paradigm. However, jointly learning a deep neural network model in a FL setting proves to be …