#machine learning
May 2026
Beyond Square Roots: Explicit Memory-Efficient Factorization for Multi-Epoch Private Learning
In the low-memory, low-bandwidth regime, $\gamma$-BIFR improves RMSE, amplified RMSE, and private training performance, while yielding tighter theoretical guarantees for multi-participation error in multi-epoch training.
Nikita P. Kalinin, Aki Rehn, Joel Daniel Andersson et al.
· arXiv.org · 1 citation