Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

Testing a Claim about Standard Deviation

Testing a Claim about Standard Deviation

A complete procedure to test a claim about population standard deviation or population variance is explained here.
The hypothesis testing for the claim of population standard deviation (or variance) requires the data and samples to be random and unbiased. The population distribution also must be normal. There is no specific requirement on the sample size as the estimation is based on the chi-square distribution.
As a first step, the hypothesis (null and alternative) concerning the claim about...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

The effects of the "ten-year fishing ban" on phytoplankton in eutrophic shallow lakes: A case study in Lake Gehu, China.

Journal of environmental management·2026

Same author

EsCA7 maintains hemocyte homeostasis and inhibits apoptosis: A mechanism of alkalinity adaptation in Eriocheir sinensis.

Developmental and comparative immunology·2026

Same author

A sensitive and cost-effective "turn-on" aptasensor for carcinoembryonic antigen using Ce-UiO-66 as an ultraefficient nanoquencher.

Mikrochimica acta·2026

Same author

Population structure and genome-wide adaptive differentiation of wild Chinese mitten crab (Eriocheir sinensis) across river basins in China.

BMC genomics·2026

Same author

Transcriptome and DNA Methylation Analyses Provide Insight into Environmental Adaptation in Northern and Southern Populations of <i>Eriocheir sinensis</i>.

Animals : an open access journal from MDPI·2026

Same author

A telomere-to-telomere reference genome assembly of the Hypomesus nipponensis.

Scientific data·2026

Search research articles

Related Experiment Video

Updated: Jun 28, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Decentralized stochastic sharpness-aware minimization algorithm.

Simiao Chen¹, Xiaoge Deng², Dongpo Xu¹

¹Key Laboratory for Applied Statistics of MOE, School of Mathematics and Statistics, Northeast Normal University, Changchun, Jilin, China.

Neural Networks : the Official Journal of the International Neural Network Society

|April 23, 2024

Summary

This summary is machine-generated.

We introduce decentralized stochastic sharpness-aware minimization (D-SSAM), a novel algorithm using distributed network topology to enhance machine learning model generalization. This approach improves test set performance for distributed stochastic algorithms.

Keywords:

Distributed optimization Generalization improvement Sharpness-aware minimization(SAM)Stochastic gradient methods

More Related Videos

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Related Experiment Videos

Last Updated: Jun 28, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Area of Science:

Machine Learning
Distributed Systems
Optimization Algorithms

Background:

Distributed stochastic algorithms are prevalent in machine learning but suffer from poor generalization.
Traditional algorithms struggle to bridge the gap between training set fitness and test set performance.
Sharpness-Aware Minimization (SAM) improves generalization by seeking flatter minima.

Purpose of the Study:

To enhance the generalization ability of distributed stochastic algorithms.
To introduce a novel algorithm, decentralized stochastic sharpness-aware minimization (D-SSAM), by integrating distributed network topology with SAM principles.
To analyze the convergence properties and empirical effectiveness of D-SSAM.

Main Methods:

Development of the decentralized stochastic sharpness-aware minimization (D-SSAM) algorithm.
Incorporation of distributed network topology into the SAM framework.
Theoretical analysis providing sublinear convergence for non-convex objectives.
Empirical validation using deep neural networks.

Main Results:

D-SSAM effectively improves the generalization ability of distributed stochastic algorithms.
Sublinear convergence rates were proven for non-convex targets, comparable to Decentralized Stochastic Gradient Descent (DSGD).
Empirical results in deep networks demonstrate the practical benefits and generalization behavior of D-SSAM.

Conclusions:

The proposed D-SSAM algorithm successfully leverages distributed network topology to enhance generalization.
D-SSAM offers a promising approach for improving the performance of machine learning models on unseen data.
The findings contribute to the understanding of generalization in distributed optimization settings.