(Amplified) Banded Matrix Factorization: A unified approach to private training. (arXiv:2306.08153v2 [cs.LG] UPDATED)

Matrix factorization (MF) mechanisms for differential privacy (DP) have
substantially improved the state-of-the-art in privacy-utility-computation
tradeoffs for ML applications in a variety of scenarios, but in both the
centralized and federated settings there remain instances where either MF
cannot be easily applied, or other algorithms provide better tradeoffs
(typically, as $\epsilon$ becomes small). In this work, we show how MF can
subsume prior state-of-the-art algorithms in both federated and centralized
training settings, across all privacy budgets. The key technique throughout …

algorithms applications art computation differential privacy federated matrix privacy private settings state training utility