arXiv Machine Learning
Curvature-Aware Clipping: Mitigating Bias in DPSGD via Approximate Second-Order Information
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 8
Differentially Private Natural Gradient Descent
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.
arXiv Machine Learning
Jun 5
DP-MacAdam: Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum
arXiv:2606. 05435v1 Announce Type: new Abstract: Differentially private stochastic gradient descent (DP-SGD) has become the standard framework for privacy-preserving machine learning, yet its reliance on a fixed gradient clipping threshold to limit sensitivity remains a significant practical limitation.
arXiv Machine Learning
Jul 27
Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
arXiv:2510. 05416v3 Announce Type: replace Abstract: Differentially private stochastic gradient descent (DP-SGD) offers the promise of training deep learning models while mitigating many privacy risks.
arXiv Machine Learning
Jul 28
DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton
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.
arXiv Machine Learning
Jun 11
Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping
arXiv:2506. 01396v2 Announce Type: replace Abstract: Differential privacy (DP) has become an essential framework for privacy-preserving machine learning.
arXiv Machine Learning
Jul 31
Quadratic Objective Perturbation: Curvature-Based Differential Privacy
arXiv:2605. 05905v2 Announce Type: replace Abstract: Objective perturbation is a standard mechanism in differentially private empirical risk minimization.