no code implementations • 14 Jun 2022 • Tharindu Adikari, Stark Draper
We present the problem of two-terminal source coding with Common Sum Reconstruction (CSR).
no code implementations • 29 Sep 2021 • Nafiseh Ghoroghchian, Rajasekhar Anguluri, Gautam Dasarathy, Stark Draper
In contrast, in this paper the controllability aspects of the coarse system are derived from coarse summaries {\em without} knowledge of the fine-scale structure.
1 code implementation • 25 Aug 2021 • Tharindu Adikari, Stark Draper
While we conclude that neither of the two heuristic methods are optimal, we also show that an optimal method does not exist.
no code implementations • 1 Jan 2021 • Tharindu Adikari, Stark Draper
To the best of our knowledge we are the first to present a gradient compression scheme that exploits temporal correlation of gradients.
no code implementations • 6 Oct 2018 • Nuwan Ferdinand, Stark Draper
In this paper, we focus on approaches to parallelizing stochastic gradient descent (SGD) wherein data is farmed out to a set of workers, the results of which, after a number of updates, are then combined at a central master node.
no code implementations • 18 Jan 2016 • Patrick Eschenfeldt, Dan Schmidt, Stark Draper, Jonathan Yedidia
We introduce a new type of graphical model that we call a "memory factor network" (MFN).