Author

Tejas D. Kulkarni

1 paper indexed here

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.

#machine learning Preprint Oct 2026

Federated Differentially Private Optimization via Low-Rank Preconditioning

A federated DP-PCA framework is proposed that achieves linear communication cost while providing central DP guarantees under secure aggregation and gives error bounds for this covariance estimate and for the resulting low-communication preconditioned DP gradient descent.

Antti Koskela, Tejas D. Kulkarni, Elias Raninen · 0 citations