paper-with-me

Papers

Generalization Bounds for Label Noise Stochastic Gradient Descent

2023-11-01 · Jung Eun Huh, Patrick Rebeschini

We develop generalization error bounds for stochastic gradient descent (SGD) with label noise in non-convex settings under uniform dissipativity and smoothness conditions. Under a suitable choice of semimetric, we establish a contraction in Wasserstein distance of the label noise stochastic gradient flow that depends polynomially on the parameter dimension $d$. Using the framework of algorithmic stability, we derive time-independent generalisation error bounds for the discretized algorithm with a constant learning rate. The error bound we achieve scales polynomially with $d$ and with the rate of $n^{-2/3}$, where $n$ is the sample size. This rate is better than the best-known rate of $n^{-1/2}$ established for stochastic gradient Langevin dynamics (SGLD) -- which employs parameter-independent Gaussian noise -- under similar conditions. Our analysis offers quantitative insights into the effect of label noise.

📄 PDF Abstract BibTeX arXiv:2311.00274

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization Bounds

Similar Papers 제목 키워드 기반

Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise

2026-01-27 · Hongxu Chen, Ke Wei, Xiaoming Yuan, Luo Luo arxiv

The empirical evidence indicates that stochastic optimization with heavy-tailed gradient noise is more appropriate to characterize the training of machine learning models than that with standard bounded gradient variance…

Stochastic Optimization

Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels

2021-02-05 · NeurIPS 2021 12 · Hao Wang, Rui Gao, Flavio P. Calmon

Machine learning models trained by different optimization algorithms under different data distributions can exhibit distinct generalization behaviors. In this paper, we analyze the generalization of models trained by noi…

Federated LearningGeneralization BoundsLearning Theory

Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise

2025-02-02 · Thanh Dang, Melih Barsbey, A K M Rokonuzzaman Sonet, Mert Gurbuzbalaban 외

Understanding the generalization properties of optimization algorithms under heavy-tailed noise has gained growing attention. However, the existing theoretical results mainly focus on stochastic gradient descent (SGD) an…

Generalization Bounds

Data-Dependent Stability of Stochastic Gradient Descent

2017-03-05 · ICML 2018 7 · Ilja Kuzborskij, Christoph H. Lampert

We establish a data-dependent notion of algorithmic stability for Stochastic Gradient Descent (SGD), and employ it to develop novel generalization bounds. This is in contrast to previous distribution-free algorithmic sta…

Generalization Bounds

Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD

2021-10-26 · NeurIPS 2021 12 · Bohan Wang, Huishuai Zhang, Jieyu Zhang, Qi Meng 외

Recently, the information-theoretical framework has been proven to be able to obtain non-vacuous generalization bounds for large models trained by Stochastic Gradient Langevin Dynamics (SGLD) with isotropic noise. In thi…

Generalization Bounds