3 citations · 3 across the 1 of their papers we have counts for
5 papers
A dual approach for federated learning
Zhenan Fan, Huang Fang, Michael P. Friedlander
We study the federated optimization problem from a dual perspective and propose a new algorithm termed federated dual coordinate descent (FedDCD), which is based on a type of coord…
Fair and efficient contribution valuation for vertical federated learning
Zhenan Fan, Huang Fang, Xinglu Wang +4
Federated learning is an emerging technology for training machine learning models across decentralized data sources without sharing data. Vertical federated learning, also known as…
Improving Fairness for Data Valuation in Horizontal Federated Learning
Zhenan Fan, Huang Fang, Zirui Zhou +4
Federated learning is an emerging decentralized machine learning scheme that allows multiple data owners to work collaboratively while ensuring data privacy. The success of federat…
Cardinality-constrained structured data-fitting problems
Zhenan Fan, Huang Fang, Michael P. Friedlander
A memory-efficient framework is described for the cardinality-constrained structured data-fitting problem. Dual-based atom-identification rules are proposed that reveal the structu…
Online mirror descent and dual averaging: keeping pace in the dynamic case
Huang Fang, Nicholas J. A. Harvey, Victor S. Portella +1
Online mirror descent (OMD) and dual averaging (DA) -- two fundamental algorithms for online convex optimization -- are known to have very similar (and sometimes identical) perform…