Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Survival Tree01:19

Survival Tree

105
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
105
Improving Translational Accuracy02:07

Improving Translational Accuracy

11.5K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.5K
Observational Learning01:12

Observational Learning

207
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
207
Associative Learning01:27

Associative Learning

434
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
434
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

79
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...
79
Load-frequency control01:28

Load-frequency control

187
Load-frequency control (LFC) is vital for maintaining power system stability, ensuring that frequency and power flows remain within acceptable limits during load changes. Turbine-governor control eliminates rotor accelerations and decelerations following load changes. However, a steady-state frequency error persists when the change in the turbine-governor reference setting is zero. In an interconnected power system, each area agrees to export or import a scheduled amount of power through...
187

You might also read

Related Articles

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

Sort by
Same author

Agent4CD: Generative Agent for Cognitive Diagnosis in Intelligent Education.

IEEE transactions on neural networks and learning systems·2026
Same author

Tidal air exposure thresholds in seagrass survival: photodamage-antioxidant imbalance and anthocyanin accumulation associated with Enhalus acoroides zonation limits.

Marine pollution bulletin·2026
Same author

MENDNet: Memory-Enhanced Dependency Network for Multistock Movement Prediction.

IEEE transactions on neural networks and learning systems·2026
Same author

MUnet: A model-based unrolled reconstruction framework for computational photoacoustic imaging.

Ultrasonics·2026
Same author

Comparison of Allo-HSCT outcomes after CAR-T therapy versus chemotherapy in pediatric patients with relapsed/refractory B-ALL: a retrospective study.

The oncologist·2026
Same author

A Weak-Magnetic-Field Measurement System with Large-Scale Uniformity and a Low Limit of Detection.

Nanomaterials (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jul 16, 2025

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
07:34

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

Published on: March 25, 2014

9.9K

Communication-efficient federated learning with stagewise training strategy.

Yifei Cheng1, Shuheng Shen2, Xianfeng Liang3

  • 1Anhui Province Key Lab of Big Data Analysis and Application, China; School of Data Science, University of Science and Technology of China, China; State Key Laboratory of Cognitive Intelligence, China.

Neural Networks : the Official Journal of the International Neural Network Society
|September 8, 2023
PubMed
Summary

This study introduces SQUARFA, an algorithm improving federated learning communication efficiency, especially with non-IID data. It achieves optimal convergence and communication complexity, addressing a key challenge in distributed machine learning.

Keywords:
Communication complexityConvergence rateFederated learningOptimization algorithm

More Related Videos

Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning
11:20

Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning

Published on: June 2, 2014

12.0K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

617

Related Experiment Videos

Last Updated: Jul 16, 2025

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
07:34

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

Published on: March 25, 2014

9.9K
Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning
11:20

Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning

Published on: June 2, 2014

12.0K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

617

Area of Science:

  • Machine Learning
  • Distributed Systems
  • Optimization Algorithms

Background:

  • Federated learning (FL) performance hinges on communication efficiency.
  • Non-independent and identically distributed (non-IID) data significantly increases communication costs in FL.
  • Existing variance reduction methods struggle to simultaneously achieve optimal communication complexity and convergence rates.

Purpose of the Study:

  • To develop an optimization algorithm that overcomes the limitations of current federated learning communication strategies.
  • To achieve simultaneous optimal communication complexity and convergence rates for FL with non-IID data.
  • To provide theoretical guarantees for both convex and non-convex optimization problems in FL.

Main Methods:

  • Proposed SQUARFA algorithm featuring a stagewise training framework with variance reduction and a quick-start phase.
  • Developed a variant of SQUARFA for general non-convex objectives.
  • Extended SQUARFA techniques to the large batch setting.

Main Results:

  • SQUARFA achieves optimal convergence rate and communication complexity for strongly convex and non-convex objectives under the PL condition.
  • A variant of SQUARFA provides optimal theoretical results for general non-convex objectives.
  • The large batch extension of SQUARFA attains optimal communication complexity.

Conclusions:

  • SQUARFA effectively addresses the communication efficiency challenges in federated learning, particularly with non-IID data.
  • The proposed algorithm offers simultaneous optimal convergence and communication complexity, filling a critical gap in FL research.
  • Experimental validation confirms the superior performance of SQUARFA and its variants.