paper-with-me

홈 › Papers

Inherent Noise in Gradient Based Methods

2020-05-26 · Arushi Gupta

Previous work has examined the ability of larger capacity neural networks to generalize better than smaller ones, even without explicit regularizers, by analyzing gradient based algorithms such as GD and SGD. The presence of noise and its effect on robustness to parameter perturbations has been linked to generalization. We examine a property of GD and SGD, namely that instead of iterating through all scalar weights in the network and updating them one by one, GD (and SGD) updates all the parameters at the same time. As a result, each parameter $w^i$ calculates its partial derivative at the stale parameter $\mathbf{w_t}$, but then suffers loss $\hat{L}(\mathbf{w_{t+1}})$. We show that this causes noise to be introduced into the optimization. We find that this noise penalizes models that are sensitive to perturbations in the weights. We find that penalties are most pronounced for batches that are currently being used to update, and are higher for larger models.

📄 PDF Abstract BibTeX arXiv:2005.12743

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

On the Inherent Privacy of Zeroth Order Projected Gradient Descent

2025-07-08 · Devansh Gupta, Meisam Razaviyayn, Vatsal Sharan arxiv

Differentially private zeroth-order optimization methods have recently gained popularity in private fine tuning of machine learning models due to their reduced memory requirements. Current approaches for privatizing zero…

Asynchronous stochastic convex optimization: the noise is in the noise and SGD don't care

2015-12-01 · NeurIPS 2015 12 · Sorathan Chaturapruek, John C. Duchi, Christopher Ré

We show that asymptotically, completely asynchronous stochastic gradient procedures achieve optimal (even to constant factors) convergence rates for the solution of convex optimization problems under nearly the same cond…

Stochastic Optimization

Asynchronous stochastic convex optimization

2015-08-04 · John C. Duchi, Sorathan Chaturapruek, Christopher Ré

We show that asymptotically, completely asynchronous stochastic gradient procedures achieve optimal (even to constant factors) convergence rates for the solution of convex optimization problems under nearly the same cond…

Stochastic Optimization

Axiomatization of Gradient Smoothing in Neural Networks

2024-06-29 · Linjiang Zhou, Xiaochuan Shi, Chao Ma, Zepeng Wang

Gradients play a pivotal role in neural networks explanation. The inherent high dimensionality and structural complexity of neural networks result in the original gradients containing a significant amount of noise. While…

Securing Distributed SGD against Gradient Leakage Threats

2023-05-10 · Wenqi Wei, Ling Liu, Jingya Zhou, Ka-Ho Chow 외

This paper presents a holistic approach to gradient leakage resilient distributed Stochastic Gradient Descent (SGD). First, we analyze two types of strategies for privacy-enhanced federated learning: (i) gradient pruning…

Federated Learning