6 papers · 1 filter
PANOC-lite: A simpler and more efficient algorithm for composite minimization
Alexander Bodard, Pieter Pas, Andreas Themelis +1
This work introduces a simple and efficient linesearch method for composite minimization that accelerates proximal-gradient iterations with fast Newton-type directions. Our algorit…
On the Regularity of Generalized Conjugate Functions
Konstantinos Oikonomidis, Emanuel Laude, Panagiotis Patrinos
We investigate regularity properties of generalized conjugate functions induced by a general coupling function and the associated generalized proximal mapping. Our main results pro…
Nonlinearly preconditioned gradient flows
Konstantinos Oikonomidis, Alexander Bodard, Jan Quan +1
We study a continuous-time dynamical system which arises as the limit of a broad class of nonlinearly preconditioned gradient methods. Under mild assumptions, we establish existenc…
Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
Konstantinos Oikonomidis, Jan Quan, Panagiotis Patrinos
We study nonlinearly preconditioned gradient methods for smooth nonconvex optimization problems, focusing on sigmoid preconditioners that inherently perform a form of gradient clip…
Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
Alexander Bodard, Panagiotis Patrinos
We study generalized smoothness in nonconvex optimization, focusing on -smoothness and anisotropic smoothness. The former was empirically derived from practical neural…
Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization
Alexander Bodard, Masoud Ahookhosh, Panagiotis Patrinos
This study introduces two second-order methods designed to provably avoid saddle points in composite nonconvex optimization problems: (i) a nonsmooth trust-region method and (ii) a…