3 papers
cs.LG2026
Decentralized Multitask Learning over Learned Task Graphs
Zirui Wan, Stefan Vlaski
This paper investigates decentralized multitask learning over networks when the underlying task relationships are unknown. While existing graph-regularized multitask frameworks typ…
cs.LG2025
Multitask Learning with Learned Task Relationships
Zirui Wan, Stefan Vlaski
Classical consensus-based strategies for federated and decentralized learning are statistically suboptimal in the presence of heterogeneous local data or task distributions. As a r…
cs.MA2023
Crowd Modeling and Control via Cooperative Adaptive Filtering
Zirui Wan, Saeid Sanei
This paper introduces a crowd modeling and motion control approach that employs diffusion adaptation within an adaptive network. In the network, nodes collaboratively address speci…