Zehan Zhu
3 papers · 2022–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Silver
๐ฃ
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
differential privacy
(2)
variance reduction
(2)
decentralized learning
(2)
non-convex optimization
(1)
distributed learning
(1)
decentralized optimization
(1)
data heterogeneity
(1)
gradient clipping
(1)
privacy budget
(1)
gaussian mechanism
(1)
gradient tracking
(1)
privacy accounting
(1)
utility guarantee
(1)
utility bound
(1)
federated learning
(1)
sample-induced topology
(1)
stochastic gradient
(1)
stochastic gradient descent
(1)
Papers
Dyn-D^2P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee
IJCAI 2025
PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds
IJCAI 2024
Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology
ICML 2022