paper-with-me

홈 › Papers

DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation

2023-04-21 · Qiaoyue Tang, Mathias Lécuyer

We observe that the traditional use of DP with the Adam optimizer introduces a bias in the second moment estimation, due to the addition of independent noise in the gradient computation. This bias leads to a different scaling for low variance parameter updates, that is inconsistent with the behavior of non-private Adam, and Adam's sign descent interpretation. Empirically, correcting the bias introduced by DP noise significantly improves the optimization performance of DP-Adam.

📄 PDF Abstract BibTeX arXiv:2304.11208

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)

2023-12-21 · Qiaoyue Tang, Frederick Shpilevskiy, Mathias Lécuyer

The Adam optimizer is a popular choice in contemporary deep learning, due to its strong empirical performance. However we observe that in privacy sensitive scenarios, the traditional use of Differential Privacy (DP) with…

Node Classification

DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models

2026-02-23 · Jin Liu, Yinbin Miao, Ning Xi, Junkang Liu arxiv

Balancing convergence efficiency and robustness under Differential Privacy (DP) is a central challenge in Federated Learning (FL). While AdamW accelerates training and fine-tuning in large-scale models, we find that dire…

Federated Learning

AdamD: Improved bias-correction in Adam

2021-10-20 · John St John

Here I present a small update to the bias-correction term in the Adam optimizer that has the advantage of making smaller gradient updates in the first several steps of training. With the default bias-correction, Adam may…

DP-AdamW: Investigating Decoupled Weight Decay and Bias Correction in Private Deep Learning

2025-11-11 · Jay Chooi, Kevin Cong, Russell Li, Lillian Sun arxiv

As deep learning methods increasingly utilize sensitive data on a widespread scale, differential privacy (DP) offers formal guarantees to protect against information leakage during model training. A significant challenge…

Image ClassificationNode ClassificationText Classification

When Can You Get Away with Low Memory Adam?

2025-03-03 · Dayal Singh Kalra, John Kirchenbauer, Maissam Barkeshli, Tom Goldstein

Adam is the go-to optimizer for training modern machine learning models, but it requires additional memory to maintain the moving averages of the gradients and their squares. While various low-memory optimizers have been…