Optimizer Dynamics at the Edge of Stability with Differential Privacy

• URL: http://arxiv.org/abs/2512.19019v1
• Date: Mon, 22 Dec 2025 04:16:13 GMT
• Title: Optimizer Dynamics at the Edge of Stability with Differential Privacy
• Authors: Ayana Hussain, Ricky Fang,
• Abstract summary: Deep learning models can reveal sensitive information about individual training examples.<n>We study the training dynamics of neural networks under differential privacy (DP)<n>These findings highlight the unpredictability introduced by DP in neural network optimization.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning models can reveal sensitive information about individual training examples, and while differential privacy (DP) provides guarantees restricting such leakage, it also alters optimization dynamics in poorly understood ways. We study the training dynamics of neural networks under DP by comparing Gradient Descent (GD), and Adam to their privacy-preserving variants. Prior work shows that these optimizers exhibit distinct stability dynamics: full-batch methods train at the Edge of Stability (EoS), while mini-batch and adaptive methods exhibit analogous edge-of-stability behavior. At these regimes, the training loss and the sharpness--the maximum eigenvalue of the training loss Hessian--exhibit certain characteristic behavior. In DP training, per-example gradient clipping and Gaussian noise modify the update rule, and it is unclear whether these stability patterns persist. We analyze how clipping and noise change sharpness and loss evolution and show that while DP generally reduces the sharpness and can prevent optimizers from fully reaching the classical stability thresholds, patterns from EoS and analogous adaptive methods stability regimes persist, with the largest learning rates and largest privacy budgets approaching, and sometimes exceeding, these thresholds. These findings highlight the unpredictability introduced by DP in neural network optimization.

Related papers

• An Adaptive Differentially Private Federated Learning Framework with Bi-level Optimization [10.218291445871435]
  Federated learning enables collaborative model training across distributed clients while preserving data privacy.<n>In practical deployments, device heterogeneity, non-independent, and identically distributed (Non-IID) data often lead to highly unstable and biased gradient updates.<n>We propose an adaptive differentially private federated learning framework that explicitly targets model efficiency under heterogeneous and privacy-constrained settings.
  arXiv  Detail & Related papers  (2026-02-06T16:27:33Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• ADP-VRSGP: Decentralized Learning with Adaptive Differential Privacy via Variance-Reduced Stochastic Gradient Push [24.62800551742178]
  We propose a novel approach called decentralized learning with adaptive differential privacy via variance-reduced gradient push.<n>This method dynamically adjusts both the noise variance and the learning rate using a stepwise-decaying schedule.<n>We show that ADP-VRSGP achieves robust convergence with an appropriate learning rate, significantly improving training stability and speed.
  arXiv  Detail & Related papers  (2025-10-23T03:14:59Z)
• Adaptive Heavy-Tailed Stochastic Gradient Descent [0.0]
  AHTSGD is the first algorithm to adjust the nature of injected noise into a generalization based on the Edge of Stability phenomenon.<n>AHTSGD consistently outperforms SGD and other noise-based methods on benchmarks like MNIST and CIFAR-10, with marked gains on noisy datasets such as SVHN.
  arXiv  Detail & Related papers  (2025-08-29T06:32:26Z)
• DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction [57.83978915843095]
  This paper introduces DiSK, a novel framework designed to significantly enhance the performance of differentially private gradients.<n>To ensure practicality for large-scale training, we simplify the Kalman filtering process, minimizing its memory and computational demands.
  arXiv  Detail & Related papers  (2024-10-04T19:30:39Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release [29.765896801370612]
  This paper proposes Differentially Private training framework based on Selective Updates and Release. The main challenges lie in two aspects -- privacy concerns, and gradient selection strategy for model update. Experiments conducted on MNIST, FMNIST, CIFAR-10, and IMDB datasets show that DPSUR significantly outperforms previous works in terms of convergence speed.
  arXiv  Detail & Related papers  (2023-11-23T15:19:30Z)
• Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy [67.33715954653098]
  We propose a novel DPFL algorithm named DP-FedSAM, which leverages gradient perturbation to mitigate the negative impact of DP. Specifically, DP-FedSAM integrates Sharpness Aware of Minimization (SAM) to generate local flatness models with stability and weight robustness. To further reduce the magnitude random noise while achieving better performance, we propose DP-FedSAM-$top_k$ by adopting the local update sparsification technique.
  arXiv  Detail & Related papers  (2023-05-01T15:19:09Z)
• Dynamic Differential-Privacy Preserving SGD [19.273542515320372]
  Differentially-Private Gradient Descent (DP-SGD) prevents training-data privacy breaches by adding noise to the clipped gradient during SGD training. The same clipping operation and additive noise across training steps results in unstable updates and even a ramp-up period. We propose the dynamic DP-SGD, which has a lower privacy cost than the DP-SGD during updates until they achieve the same target privacy budget.
  arXiv  Detail & Related papers  (2021-10-30T04:45:11Z)
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations [54.23691425062034]
  We study the continuous-time dynamics induced by GAN training. From this perspective, we hypothesise that instabilities in training GANs arise from the integration error. We experimentally verify that well-known ODE solvers (such as Runge-Kutta) can stabilise training.
  arXiv  Detail & Related papers  (2020-10-28T15:23:49Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.