32 citations · 80 across the 15 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022
Formal guarantees for heuristic optimization algorithms used in machine learning
Xiaoyu Li
Recently, Stochastic Gradient Descent (SGD) and its variants have become the dominant methods in the large-scale optimization of machine learning (ML) problems. A variety of strate…
stat.ML2022★ 1 cited
On Distributed Adaptive Optimization with Gradient Compression
Xiaoyun Li, Belhal Karimi, Ping Li
We study COMP-AMS, a distributed optimization framework based on gradient averaging and adaptive AMSGrad algorithm. Gradient compression with error feedback is applied to reduce th…