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...
المؤلفون الرئيسيون: | Richards, D, Rebeschini, P, Rosasco, L |
---|---|
التنسيق: | Conference item |
اللغة: | English |
منشور في: |
Proceedings of Machine Learning Research
2020
|
مواد مشابهة
-
Robust gradient descent for phase retrieval
حسب: Buna-Marginean, A, وآخرون
منشور في: (2025) -
Graph-dependent implicit regularisation for distributed stochastic subgradient descent
حسب: Richards, D, وآخرون
منشور في: (2020) -
Generalization bounds for label noise stochastic gradient descent
حسب: Huh, JE, وآخرون
منشور في: (2023) -
Generalization bounds for label noise stochastic gradient descent
حسب: Huh, JE, وآخرون
منشور في: (2024) -
Optimal statistical rates for decentralised non-parametric regression with linear speed-up
حسب: Richards, D, وآخرون
منشور في: (2019)