3 citations · 4 across the 4 of their papers we have counts for
Showing 2017 · cs.DCShow all
2 papers · 2 filters
cs.DC2017
Avoiding Synchronization in First-Order Methods for Sparse Convex Optimization
Aditya Devarakonda, Kimon Fountoulakis, James Demmel +1
Parallel computing has played an important role in speeding up convex optimization methods for big data analytics and large-scale machine learning (ML). However, the scalability of…
cs.DC2017★ 3 cited
Avoiding Communication in Proximal Methods for Convex Optimization Problems
Saeed Soori, Aditya Devarakonda, James Demmel +2
The fast iterative soft thresholding algorithm (FISTA) is used to solve convex regularized optimization problems in machine learning. Distributed implementations of the algorithm h…