Decentralised learning with distributed gradient descent and random features
We investigate the generalisation performance of Distributed Gradient Descent with implicit regularisation and random features in the homogenous setting where a network of agents are given data sampled independently from the same unknown distribution. Along with reducing the memory footprint, random...
Main Authors: | Richards, D, Rebeschini, P, Rosasco, L |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Proceedings of Machine Learning Research
2020
|
Similar Items
-
Robust gradient descent for phase retrieval
by: Buna-Marginean, A, et al.
Published: (2025) -
Graph-dependent implicit regularisation for distributed stochastic subgradient descent
by: Richards, D, et al.
Published: (2020) -
Generalization bounds for label noise stochastic gradient descent
by: Huh, JE, et al.
Published: (2023) -
Generalization bounds for label noise stochastic gradient descent
by: Huh, JE, et al.
Published: (2024) -
Optimal statistical rates for decentralised non-parametric regression with linear speed-up
by: Richards, D, et al.
Published: (2019)