Under bounded second-order heterogeneity, local updates are shown to achieve faster convergence than mini-batch SGD in several convex and non-convex regimes, with matching lower bounds.
Addressing modern and practical challenges in machine learning: A survey of online federated and transfer learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Online federated learning (OFL) and online transfer learning (OTL) are two collaborative paradigms for overcoming modern machine learning challenges such as data silos, streaming data, and data security. This survey explored OFL and OTL throughout their major evolutionary routes to enhance understanding of online federated and transfer learning. Besides, practical aspects of popular datasets and cutting-edge applications for online federated and transfer learning are highlighted in this work. Furthermore, this survey provides insight into potential future research areas and aims to serve as a resource for professionals developing online federated and transfer learning frameworks.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What Makes Local Updates Effective: The Role of Data Heterogeneity and Smoothness
Under bounded second-order heterogeneity, local updates are shown to achieve faster convergence than mini-batch SGD in several convex and non-convex regimes, with matching lower bounds.