Publication

SCAFFOLD Stochastic Controlled Averaging for Federated Learning

Sai Praneeth Reddy Karimireddy, Sebastian Urban Stich, Ananda Theertha Suresh
2020
Conference Papers

Abstract

Federated Averaging (FEDAVG) has emerged as the algorithm of choice for federated learning due to its simplicity and low communication cost. However, in spite of recent research efforts, its performance is not fully understood. We obtain tight convergence rates for FEDAVG and prove that it suffers from 'client-drift' when the data is heterogeneous (non-iid), resulting in unstable and slow convergence.

Official source

https://infoscience.epfl.ch/entities/publication/f58f5ef3-2e36-4a6a-9f9b-fa56a65e90a4

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Sai Praneeth Reddy Karimireddy, Sebastian Urban Stich, Ananda Theertha Suresh
2020
Conference Papers

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/f58f5ef3-2e36-4a6a-9f9b-fa56a65e90a4

About this result

Related concepts (18)

Rate of convergence

In numerical analysis, the order of convergence and the rate of convergence of a convergent sequence are quantities that represent how quickly the sequence approaches its limit. A sequence that converges to is said to have order of convergence and rate of convergence if The rate of convergence is also called the asymptotic error constant. Note that this terminology is not standardized and some authors will use rate where this article uses order (e.g., ).

Data

In common usage and statistics, data (USˈdætə; UKˈdeɪtə) is a collection of discrete or continuous values that convey information, describing the quantity, quality, fact, statistics, other basic units of meaning, or simply sequences of symbols that may be further interpreted formally. A datum is an individual value in a collection of data. Data is usually organized into structures such as tables that provide additional context and meaning, and which may themselves be used as data in larger structures.

Big data

Big data primarily refers to data sets that are too large or complex to be dealt with by traditional data-processing application software. Data with many entries (rows) offer greater statistical power, while data with higher complexity (more attributes or columns) may lead to a higher false discovery rate. Though used sometimes loosely partly because of a lack of formal definition, the interpretation that seems to best describe big data is the one associated with a large body of information that we could not comprehend when used only in smaller amounts.

Related publications (30)

Nanoindentation hardness and modulus of Al2O3-SiO2-CaO and MnO-SiO2-FeO inclusions in iron

Andreas Mortensen, Léa Deillon, Alejandra Inés Slagter, Eva Luisa Vogt, David Hernandez Escobar, Jonathan Aristya Setyadji

Dataset corresponding to the following manuscript: Slagter, A., Setyadji, J.A., Vogt, E.L. et al. Nanoindentation Hardness and Modulus of Al2O3–SiO2–CaO and MnO–SiO2–FeO Inclusions in Iron. Metall Mater Trans A (2024). https://doi.org/10.1007/s11661-024-0 ...

Zenodo2024

Data and scripts for the RaFSIP scheme

Athanasios Nenes, Paraskevi Georgakaki

This repository contains microphysics routines, scripts, and processed data from the Weather Research and Forecasting (WRF) model simulations presented in the paper "RaFSIP: Parameterizing ice multiplication in models using a machine learning approach", by ...

Zenodo2024

Data-driven statistical optimization of a groundwater monitoring network

Andrea Rinaldo, Gianluca Botter

We propose a comparative study of three different methods aimed at optimizing existing groundwater monitoring networks. Monitoring piezometric heads in subsurface porous formations is crucial at regional scales to properly characterize the relevant subsurf ...

Elsevier2024