Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent

• URL: http://arxiv.org/abs/2606.12054v1
• Date: Wed, 10 Jun 2026 13:19:24 GMT
• Title: Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent
• Abstract summary: Injecting noise into the optimization process is a well-established technique for improving the training and generalization of deep neural networks.<n>We focus on two key questions: how to efficiently pair each training example with its own perturbation in mini-batch training, and whether sophisticated noise parameterizations or multi-sample gradient averaging yield meaningful gains.<n>Our results consistently show that simple, lightweight perturbation strategies, isotropic noise with a single forward pass per update step, recover most of the benefit of more complex schemes.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Injecting noise into the optimization process is a well-established technique for improving the training and generalization of deep neural networks. Yet, despite the breadth of existing approaches, it remains unclear which design choices truly matter in practice. In this work, we investigate parameter noise injection for stochastic gradient descent, focusing on two key questions: how to efficiently pair each training example with its own perturbation in mini-batch training, and whether sophisticated noise parameterizations or multi-sample gradient averaging yield meaningful gains over simpler alternatives. To address the first question, we leverage a distributional identity for linear layers that allows per-example noise injection without breaking batched computation. To address the second, we systematically compare several diagonal Gaussian parameterizations against an isotropic baseline across varying noise levels on CIFAR100. Our results consistently show that simple, lightweight strategies, isotropic noise with a single perturbed forward pass per update step, recover most of the benefit of more complex schemes. These findings suggest that simplicity suffices for parameter noise injection, and that practitioners need not resort to elaborate perturbation designs to reap the optimization and generalization benefits of noisy SGD.

Related papers

• SHANG++: Robust Stochastic Acceleration under Multiplicative Noise [6.759434764396595]
  We develop two accelerated gradient descent methods by discretizing the Hessian-driven Nesterov accelerated gradient flow.<n>SHANG++ adds a damping correction and achieves faster convergence with stronger noise robustness.<n>In our experiments, SHANG++ performs consistently well across convex problems and applications in deep learning.
  arXiv  Detail & Related papers  (2026-03-10T08:35:53Z)
• Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits [53.773695219320125]
  We take a first step toward a theoretical understanding of second-order optimization under heavy-tailed noise.<n>We introduce a novel algorithm based on gradient and Hessian clipping, and prove high-probability upper bounds that nearly match the fundamental limits.
  arXiv  Detail & Related papers  (2025-10-12T16:36:54Z)
• Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance [52.705112811734566]
  A novel diffusion-based framework is introduced for solving inverse problems using a piecewise guidance scheme.<n>The proposed method is problem-agnostic and readily adaptable to a variety of inverse problems.<n>The framework achieves a reduction in inference time of (25%) for inpainting with both random and center masks, and (23%) and (24%) for (4times) and (8times) super-resolution tasks.
  arXiv  Detail & Related papers  (2025-07-22T19:35:14Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• Latent Class-Conditional Noise Model [54.56899309997246]
  We introduce a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples.
  arXiv  Detail & Related papers  (2023-02-19T15:24:37Z)
• Improve Noise Tolerance of Robust Loss via Noise-Awareness [60.34670515595074]
  We propose a meta-learning method which is capable of adaptively learning a hyper parameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster for brevity) Four SOTA robust loss functions are attempted to be integrated with our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its noise tolerance and performance.
  arXiv  Detail & Related papers  (2023-01-18T04:54:58Z)
• Tradeoffs between convergence rate and noise amplification for momentum-based accelerated optimization algorithms [8.669461942767098]
  We study momentum-based first-order optimization algorithms in which the iterations are subject to an additive white noise. For strongly convex quadratic problems, we use the steady-state variance of the error in the optimization variable to quantify noise amplification. We introduce two parameterized families of algorithms that strike a balance between noise amplification and settling time.
  arXiv  Detail & Related papers  (2022-09-24T04:26:30Z)
• Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery [8.581512812219737]
  We propose a new framework for low-rank matrix recovery from observations corrupted with noise and outliers. Inspired by the square root Lasso, this new formulation does not require prior knowledge of the noise level. We show that a single, universal choice of the regularization parameter suffices to achieve reconstruction error proportional to the (a priori unknown) noise level.
  arXiv  Detail & Related papers  (2021-06-17T02:28:11Z)
• 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)
• Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering [53.523517926927894]
  We explore the use of exact per-sample Hessian-vector products and gradients to construct self-tuning quadratics. We prove that our model-based procedure converges in noisy gradient setting. This is an interesting step for constructing self-tuning quadratics.
  arXiv  Detail & Related papers  (2020-11-09T22:07:30Z)
• 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)
• Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic [5.395127324484869]
  SplitSGD is a new dynamic learning schedule for optimization. The method decreases the learning rate for better adaptation to the local geometry of the objective function. It essentially does not incur additional computational cost than standard SGD.
  arXiv  Detail & Related papers  (2019-10-18T19:38:53Z)

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.