English

DP-MicroAdam: Private and Frugal Algorithm for Training and Fine-tuning

Machine Learning 2025-12-01 v2

Abstract

Adaptive optimizers are the de facto standard in non-private training as they often enable faster convergence and improved performance. In contrast, differentially private (DP) training is still predominantly performed with DP-SGD, typically requiring extensive compute and hyperparameter tuning. We propose DP-MicroAdam, a memory-efficient and sparsity-aware adaptive DP optimizer. We prove that DP-MicroAdam converges in stochastic non-convex optimization at the optimal O(1/T)\mathcal{O}(1/\sqrt{T}) rate, up to privacy-dependent constants. Empirically, DP-MicroAdam outperforms existing adaptive DP optimizers and achieves competitive or superior accuracy compared to DP-SGD across a range of benchmarks, including CIFAR-10, large-scale ImageNet training, and private fine-tuning of pretrained transformers. These results demonstrate that adaptive optimization can improve both performance and stability under differential privacy.

Keywords

Cite

@article{arxiv.2511.20509,
  title  = {DP-MicroAdam: Private and Frugal Algorithm for Training and Fine-tuning},
  author = {Mihaela Hudişteanu and Nikita P. Kalinin and Edwige Cyffers},
  journal= {arXiv preprint arXiv:2511.20509},
  year   = {2025}
}
R2 v1 2026-07-01T07:54:34.617Z