605 citations · 1.2k across the 17 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.LG2017★ 605 cited
Visualizing the Loss Landscape of Neural Nets
Hao Li, Zheng Xu, Gavin Taylor +2
Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip…
cs.LG2017★ 37 cited
Adaptive Consensus ADMM for Distributed Optimization
Zheng Xu, Gavin Taylor, Hao Li +3
The alternating direction method of multipliers (ADMM) is commonly used for distributed model fitting problems, but its performance and reliability depend strongly on user-defined…