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) 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.
@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}
}