2 citations · 4 across the 2 of their papers we have counts for
6 papers
High-order methods beyond the classical complexity bounds, II: inexact high-order proximal-point methods with segment search
Masoud Ahookhosh, Yurii Nesterov
A bi-level optimization framework (BiOPT) was proposed in [3] for convex composite optimization, which is a generalization of bi-level unconstrained minimization framework (BLUM) g…
High-order methods beyond the classical complexity bounds, I: inexact high-order proximal-point methods
Masoud Ahookhosh, Yurii Nesterov
In this paper, we introduce a \textit{Bi-level OPTimization} (BiOPT) framework for minimizing the sum of two convex functions, where both can be nonsmooth. The BiOPT framework invo…
A block inertial Bregman proximal algorithm for nonsmooth nonconvex problems with application to symmetric nonnegative matrix tri-factorization
Masoud Ahookhosh, Le Thi Khanh Hien, Nicolas Gillis +1
We propose BIBPA, a block inertial Bregman proximal algorithm for minimizing the sum of a block relatively smooth function (that is, relatively smooth concerning each block) and bl…
Finding Zeros of Hölder Metrically Subregular Mappings via Globally Convergent Levenberg-Marquardt Methods
Masoud Ahookhosh, Ronan M. T. Fleming, Phan T. Vuong
We present two globally convergent Levenberg-Marquardt methods for finding zeros of Hölder metrically subregular mappings that may have non-isolated zeros. The first method unifies…
On the acceleration of forward-backward splitting via an inexact Newton method
Andreas Themelis, Masoud Ahookhosh, Panagiotis Patrinos
We propose a Forward-Backward Truncated-Newton method (FBTN) for minimizing the sum of two convex functions, one of which smooth. Unlike other proximal Newton methods, our approach…
Accelerated first-order methods for large-scale convex minimization
Masoud Ahookhosh
This paper discusses several (sub)gradient methods attaining the optimal complexity for smooth problems with Lipschitz continuous gradients, nonsmooth problems with bounded variati…