Login / Signup
(Near) Optimal Parallelism Bound for Fully Asynchronous Coordinate Descent with Linear Speedup.
Yun Kuen Cheung
Richard Cole
Yixin Tao
Published in:
CoRR (2018)
Keyphrases
</>
orders of magnitude
upper bound
worst case
lower bound
neural network
logistic regression
quadratic programming
shift register
data parallelism
asynchronous communication
fine grain
linear systems
brute force
parallel processing
error bounds
closed form
markov random field
query processing
pairwise