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...
主要な著者: | Richards, D, Rebeschini, P, Rosasco, L |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
Proceedings of Machine Learning Research
2020
|
類似資料
-
Robust gradient descent for phase retrieval
著者:: Buna-Marginean, A, 等
出版事項: (2025) -
Graph-dependent implicit regularisation for distributed stochastic subgradient descent
著者:: Richards, D, 等
出版事項: (2020) -
Generalization bounds for label noise stochastic gradient descent
著者:: Huh, JE, 等
出版事項: (2023) -
Generalization bounds for label noise stochastic gradient descent
著者:: Huh, JE, 等
出版事項: (2024) -
Optimal statistical rates for decentralised non-parametric regression with linear speed-up
著者:: Richards, D, 等
出版事項: (2019)