arXiv:2506. 01396v2 Announce Type: replace Abstract: Differential privacy (DP) has become an essential framework for privacy-preserving machine learning.
By Linzh Zhao, Aki Rehn, Mikko A. Heikkil\"a, Razane Tajeddine, Antti Honkela
arXiv:2607. 05866v1 Announce Type: cross Abstract: Under a fixed privacy budget, the utility of differentially private (DP) training is ultimately determined by its optimization efficiency.
By Pan Li, Kai Chen, Shuai Chang, Shengzhi Zhang, Peizhuo Lv, Jinwen He
arXiv:2607. 23649v1 Announce Type: new Abstract: Differential privacy provides formal privacy guarantees for training neural networks on sensitive data, while Bayesian deep learning offers a principled framework for uncertainty-aware prediction.
By Nour Jamoussi, Ikram Dridi, Giuseppe Serra, Marios Kountouris
arXiv:2605. 02701v2 Announce Type: replace-cross Abstract: We propose a robust gradient estimator based on per-sample gradient clipping and analyze its properties both theoretically and empirically.
By Davide Nobile, Philipp Grohs
Machine learning's reliance on sensitive data necessitates privacy-preserving techniques like Differentially Private Stochastic Gradient Descent (DPSGD). However, DPSGD suffers from substantial utility degradation and slow convergence due to gradient clipping and noise injection.
The paper proves that stochastic gradient descent with gradient clipping and additive Gaussian noise (SGD‑CN) converges almost surely under smoothness and bounded noise assumptions, given standard decaying step sizes. The analysis extends to momentum variants such as the stochastic heavy ball and Nesterov's accelerated gradient, showing that careful energy constructions yield similar guarantees. These results provide stronger theoretical foundations for understanding the pathwise behaviour of clipped stochastic gradient methods in both convex and nonconvex regimes.
By Amartya Mukherjee, Jun Liu