Better Worst-Case Complexity Analysis of the Block Coordinate Descent Method for Large Scale Machine Learning

Author(s):  
Ziqiang Shi ◽  
Rujie Liu
2017 ◽  
Vol 82 (2) ◽  
pp. 672-708 ◽  
Author(s):  
FEDERICO ASCHIERI

AbstractWe present abstract complexity results about Coquand and Hyland–Ong game semantics, that will lead to new bounds on the length of first-order cut-elimination, normalization, interaction between expansion trees and any other dialogical process game semantics can model and apply to. In particular, we provide a novel method to bound the length of interactions between visible strategies and to measure precisely the tower of exponentials defining the worst-case complexity. Our study improves the old estimates on average by several exponentials.


Sign in / Sign up

Export Citation Format

Share Document