pFedSOP combines Gompertz-weighted local/global gradients with a rank-one Fisher Information Matrix update to speed up personalized federated learning, but the convergence proof is invalid and the update reduces to normalized gradient descent.
On Second-order Optimization Methods for Federated Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We consider federated learning (FL), where the training data is distributed across a large number of clients. The standard optimization method in this setting is Federated Averaging (FedAvg), which performs multiple local first-order optimization steps between communication rounds. In this work, we evaluate the performance of several second-order distributed methods with local steps in the FL setting which promise to have favorable convergence properties. We (i) show that FedAvg performs surprisingly well against its second-order competitors when evaluated under fair metrics (equal amount of local computations)-in contrast to the results of previous work. Based on our numerical study, we propose (ii) a novel variant that uses second-order local information for updates and a global line search to counteract the resulting local specificity.
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
pFedSOP : Accelerating Training Of Personalized Federated Learning Using Second-Order Optimization
pFedSOP combines Gompertz-weighted local/global gradients with a rank-one Fisher Information Matrix update to speed up personalized federated learning, but the convergence proof is invalid and the update reduces to normalized gradient descent.