Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Johnstone, Patrick R."'
Publikováno v:
Stat. Anal. Data Min.: ASA Data Sci. J. 17 (2024)
One among several advantages of measure transport methods is that they allow for a unified framework for processing and analysis of data distributed according to a wide class of probability measures. Within this context, we present results from compu
Externí odkaz:
http://arxiv.org/abs/2309.15366
We present a new, stochastic variant of the projective splitting (PS) family of algorithms for monotone inclusion problems. It can solve min-max and noncooperative game formulations arising in applications such as robust ML without the convergence is
Externí odkaz:
http://arxiv.org/abs/2106.13067
This work describes a new variant of projective splitting for solving maximal monotone inclusions and complicated convex optimization problems. In the new version, cocoercive operators can be processed with a single forward step per iteration. In the
Externí odkaz:
http://arxiv.org/abs/1902.09025
Autor:
Johnstone, Patrick R.1 (AUTHOR) patrick.r.johnstone@gmail.com, Eckstein, Jonathan2 (AUTHOR), Flynn, Thomas1 (AUTHOR), Yoo, Shinjae1 (AUTHOR)
Publikováno v:
Computational Optimization & Applications. Mar2024, Vol. 87 Issue 2, p397-437. 41p.
Publikováno v:
Optim. Lett. 14, 229-247 (2020)
A recent innovation in projective splitting algorithms for monotone operator inclusions has been the development of a procedure using two forward steps instead of the customary proximal steps for operators that are Lipschitz continuous. This paper sh
Externí odkaz:
http://arxiv.org/abs/1809.07180
Publikováno v:
SIAM J. Optim., 29(3), 1931-1957. (27 pages)
Projective splitting is a family of methods for solving inclusions involving sums of maximal monotone operators. First introduced by Eckstein and Svaiter in 2008, these methods have enjoyed significant innovation in recent years, becoming one of the
Externí odkaz:
http://arxiv.org/abs/1806.03920
This work is concerned with the classical problem of finding a zero of a sum of maximal monotone operators. For the projective splitting framework recently proposed by Combettes and Eckstein, we show how to replace the fundamental subproblem calculat
Externí odkaz:
http://arxiv.org/abs/1803.07043
Autor:
Johnstone, Patrick R., Moulin, Pierre
Publikováno v:
Math. Program. 180, 417-450 (2020)
The purpose of this manuscript is to derive new convergence results for several subgradient methods applied to minimizing nonsmooth convex functions with H\"olderian growth. The growth condition is satisfied in many applications and includes function
Externí odkaz:
http://arxiv.org/abs/1704.00196
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Johnstone, Patrick R., Moulin, Pierre
We study the convergence properties of a general inertial first-order proximal splitting algorithm for solving nonconvex nonsmooth optimization problems. Using the Kurdyka--\L ojaziewicz (KL) inequality we establish new convergence rates which apply
Externí odkaz:
http://arxiv.org/abs/1609.03626