The Uniform Hardcore Lemma via Approximate Bregman Projections

Author(s):  
Boaz Barak ◽  
Moritz Hardt ◽  
Satyen Kale
Keyword(s):  
2002 ◽  
Vol 13 (1) ◽  
pp. 283-297 ◽  
Author(s):  
Yair Censor ◽  
Gabor T. Herman

Optimization ◽  
2000 ◽  
Vol 48 (4) ◽  
pp. 409-427 ◽  
Author(s):  
Heinz H Bauschke ◽  
Adrian S Lewis

2015 ◽  
Vol 37 (2) ◽  
pp. A1111-A1138 ◽  
Author(s):  
Jean-David Benamou ◽  
Guillaume Carlier ◽  
Marco Cuturi ◽  
Luca Nenna ◽  
Gabriel Peyré

Author(s):  
Ahmet Alacaoglu ◽  
Yura Malitsky ◽  
Volkan Cevher

AbstractWe propose a variance reduced algorithm for solving monotone variational inequalities. Without assuming strong monotonicity, cocoercivity, or boundedness of the domain, we prove almost sure convergence of the iterates generated by the algorithm to a solution. In the monotone case, the ergodic average converges with the optimal O(1/k) rate of convergence. When strong monotonicity is assumed, the algorithm converges linearly, without requiring the knowledge of strong monotonicity constant. We finalize with extensions and applications of our results to monotone inclusions, a class of non-monotone variational inequalities and Bregman projections.


1994 ◽  
Vol 8 (2) ◽  
pp. 221-239 ◽  
Author(s):  
Yair Censor ◽  
Tommy Elfving

Sign in / Sign up

Export Citation Format

Share Document