3 citations · 3 across the 3 of their papers we have counts for
4 papers
Decentralized optimization with non-identical sampling in presence of stragglers
Tharindu Adikari, Stark Draper
We consider decentralized consensus optimization when workers sample data from non-identical distributions and perform variable amounts of work due to slow nodes known as straggler…
Rate distortion comparison of a few gradient quantizers
Tharindu Adikari
This article is in the context of gradient compression. Gradient compression is a popular technique for mitigating the communication bottleneck observed when training large machine…
Compressing gradients by exploiting temporal correlation in momentum-SGD
Tharindu B. Adikari, Stark C. Draper
An increasing bottleneck in decentralized optimization is communication. Bigger models and growing datasets mean that decentralization of computation is important and that the amou…
Efficient learning of neighbor representations for boundary trees and forests
Tharindu Adikari, Stark C. Draper
We introduce a semiparametric approach to neighbor-based classification. We build off the recently proposed Boundary Trees algorithm by Mathy et al.(2015) which enables fast neighb…