Author

Yu-Cheng Jin

h-index 1 View on Semantic Scholar

We have 1 of 17 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

How Much Regularization Survives Averaging? Update Masking in Federated Learning

It is proved that when each client draws its own mask, federated averaging weakens that charge by exactly the cohort size, and that giving every client the same mask brings it back by a factor equal to the inverse gradient diversity of the cohort.

Wenhao Yan, Fu Kuroda, Yu-Cheng Jin et al. · 0 citations