Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level

• URL: http://arxiv.org/abs/2507.23512v1
• Date: Thu, 31 Jul 2025 12:48:29 GMT
• Title: Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
• Authors: Saleh Vatan Khah, Savelii Chezhegov, Shahrokh Farahmand, Samuel Horváth, Eduard Gorbunov,
• Abstract summary: We provide the first high-probability convergence analysis for DP with a fixed clipping level.<n>Our results show that, with a fixed clipping level, the method converges to a neighborhood optimal solution with a faster rate than the existing ones.<n>The neighborhood is balanced against the noise introduced by DP, providing a refined trade-off between convergence speed and privacy guarantees.
• Score: 12.47309834217498
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Gradient clipping is a fundamental tool in Deep Learning, improving the high-probability convergence of stochastic first-order methods like SGD, AdaGrad, and Adam under heavy-tailed noise, which is common in training large language models. It is also a crucial component of Differential Privacy (DP) mechanisms. However, existing high-probability convergence analyses typically require the clipping threshold to increase with the number of optimization steps, which is incompatible with standard DP mechanisms like the Gaussian mechanism. In this work, we close this gap by providing the first high-probability convergence analysis for DP-Clipped-SGD with a fixed clipping level, applicable to both convex and non-convex smooth optimization under heavy-tailed noise, characterized by a bounded central $\alpha$-th moment assumption, $\alpha \in (1,2]$. Our results show that, with a fixed clipping level, the method converges to a neighborhood of the optimal solution with a faster rate than the existing ones. The neighborhood can be balanced against the noise introduced by DP, providing a refined trade-off between convergence speed and privacy guarantees.

Related papers

• Convergence of Clipped-SGD for Convex $(L_0,L_1)$-Smooth Optimization with Heavy-Tailed Noise [60.17850744118546]
  First-order methods with clipping, such as Clip-SGD, exhibit stronger convergence guarantees than SGD under the $(L_$1)$-smoothness assumption.<n>We establish the first high-probability convergence bounds for Clip-SGD applied to convex $(L_$1)$-smooth optimization with heavytailed noise.
  arXiv  Detail & Related papers  (2025-05-27T07:23:42Z)
• Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy [11.356444450240799]
  existing algorithms do not achieve Strong Differential Privacy (DP) and Optimization guarantees at once.<n>We propose a new method called Clip21-SGD2M based on a novel combination of clipping, heavy-ball momentum, and Error Feedback.
  arXiv  Detail & Related papers  (2025-02-17T11:16:21Z)
• On the Convergence of DP-SGD with Adaptive Clipping [56.24689348875711]
  Gradient Descent with gradient clipping is a powerful technique for enabling differentially private optimization.<n>This paper provides the first comprehensive convergence analysis of SGD with quantile clipping (QC-SGD)<n>We show how QC-SGD suffers from a bias problem similar to constant-threshold clipped SGD but can be mitigated through a carefully designed quantile and step size schedule.
  arXiv  Detail & Related papers  (2024-12-27T20:29:47Z)
• Gradient Normalization Provably Benefits Nonconvex SGD under Heavy-Tailed Noise [60.92029979853314]
  We investigate the roles of gradient normalization and clipping in ensuring the convergence of Gradient Descent (SGD) under heavy-tailed noise. Our work provides the first theoretical evidence demonstrating the benefits of gradient normalization in SGD under heavy-tailed noise. We introduce an accelerated SGD variant incorporating gradient normalization and clipping, further enhancing convergence rates under heavy-tailed noise.
  arXiv  Detail & Related papers  (2024-10-21T22:40:42Z)
• From Gradient Clipping to Normalization for Heavy Tailed SGD [19.369399536643773]
  Recent empirical evidence indicates that machine learning applications involve heavy-tailed noise, which challenges the standard assumptions of bounded variance in practice.<n>In this paper, we show that it is possible to achieve tightness of the gradient-dependent noise convergence problem under tailed noise.
  arXiv  Detail & Related papers  (2024-10-17T17:59:01Z)
• Noise is All You Need: Private Second-Order Convergence of Noisy SGD [15.31952197599396]
  We show that noise necessary for privacy already implies second-order convergence under the standard smoothness assumptions. We get second-order convergence essentially for free: DP-SGD, the workhorse of modern private optimization, under minimal assumptions can be used to find a second-order stationary point.
  arXiv  Detail & Related papers  (2024-10-09T13:43:17Z)
• Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization [94.06564567766475]
  DP-SGD and DP-NSGD mitigate the risk of large models memorizing sensitive training data. We show that these two algorithms achieve similar best accuracy while DP-NSGD is comparatively easier to tune than DP-SGD.
  arXiv  Detail & Related papers  (2022-06-27T03:45:02Z)
• Utilising the CLT Structure in Stochastic Gradient based Sampling : Improved Analysis and Faster Algorithms [14.174806471635403]
  We consider approximations of sampling algorithms, such as Gradient Langevin Dynamics (SGLD) and the Random Batch Method (RBM) for Interacting Particle Dynamcs (IPD) We observe that the noise introduced by the approximation is nearly Gaussian due to the Central Limit Theorem (CLT) while the driving Brownian motion is exactly Gaussian. We harness this structure to absorb the approximation error inside the diffusion process, and obtain improved convergence guarantees for these algorithms.
  arXiv  Detail & Related papers  (2022-06-08T10:17:40Z)
• Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process [56.55075925645864]
  The problem of constrained decision process (CMDP) is investigated, where an agent aims to maximize the expected accumulated discounted reward subject to multiple constraints. A new utilities-dual convex approach is proposed with novel integration of three ingredients: regularized policy, dual regularizer, and Nesterov's gradient descent dual. This is the first demonstration that nonconcave CMDP problems can attain the lower bound of $mathcal O (1/epsilon)$ for all complexity optimization subject to convex constraints.
  arXiv  Detail & Related papers  (2021-10-20T02:57:21Z)
• High Probability Complexity Bounds for Non-Smooth Stochastic Optimization with Heavy-Tailed Noise [51.31435087414348]
  It is essential to theoretically guarantee that algorithms provide small objective residual with high probability. Existing methods for non-smooth convex optimization have complexity bounds with dependence on confidence level. We propose novel stepsize rules for two methods with gradient clipping.
  arXiv  Detail & Related papers  (2021-06-10T17:54:21Z)
• Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping [69.9674326582747]
  We propose a new accelerated first-order method called clipped-SSTM for smooth convex optimization with heavy-tailed distributed noise in gradients. We prove new complexity that outperform state-of-the-art results in this case. We derive the first non-trivial high-probability complexity bounds for SGD with clipping without light-tails assumption on the noise.
  arXiv  Detail & Related papers  (2020-05-21T17:05:27Z)

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.