WA2a.2

Mode Connectivity in Federated Learning with Data Heterogeneity

Tailin Zhou, Jun Zhang, The Hong Kong University of Science and Technology, China; Danny H.K. Tsang, The Hong Kong University of Science and Technology (Guangzhou) and The Hong Kong University of Science and Technology, China
Session:
WA2a: Networked Optimization (Invited) Lecture
Track:
Networks
Location:
Oak Shelter
Presentation Time:
Wed, 1 Nov, 08:40 - 09:05 PT (UTC -7)
Session Co-Chairs:
Marie Maros, Purdue University and Ying Sun, Pennsylvania State University
Presentation
Discussion
Resources
No resources available.
Session WA2a
WA2a.1: Variance Reduced Stochastic Optimization over Directed Graphs with Row and Column Stochastic Weights
Muhammad Ibrahim Qureshi, Tufts University, United States; Ran Xin, Soummya Kar, Carnegie Mellon University, United States; Usman Khan, Tufts University, United States
WA2a.2: Mode Connectivity in Federated Learning with Data Heterogeneity
Tailin Zhou, Jun Zhang, The Hong Kong University of Science and Technology, China; Danny H.K. Tsang, The Hong Kong University of Science and Technology (Guangzhou) and The Hong Kong University of Science and Technology, China
WA2a.3: Distributed Stochastic Optimization with Gradient Tracking over Time-Varying Directed Networks
Duong Thuy Anh Nguyen, Duong Tung Nguyen, Angelia Nedić, Arizona State University, United States
WA2a.4: Decentralized High-Dimensional M-Estimation: A Unified View
Marie Maros, Gesualdo Scutari, Purdue University, United States
Contacts