Masoud Ahookhosh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Masoud Ahookhosh has a total of 90 co-authors. Here are the top co-authors by number of shared publications:
- Keyvan Amini
Department of Mathematics, Faculty of Science, Razi University, Kermanshah, Iran
10 shared publications - Alireza Kabgani
Department of Mathematics, University of Antwerp, Antwerp, Belgium
8 shared publications - Arnold Neumaier
Fakultät für Mathematik, Universität Wien, Wien, Austria
6 shared publications - Panagiotis Patrinos
STADIUS, KU Leuven, Leuven, Belgium
6 shared publications - Phan Tu Vuong
School of Mathematical Sciences, University of Southampton, Southampton, UK
4 shared publications - Ronan M. T. Fleming
School of Medicine, University of Galway, Galway, Ireland
4 shared publications
Latest Publications
- 2 November 2026
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Optimization
- Vol. 36 (4) , 2387-2416
ItsOPT: An Inexact Two-Level Smoothing Framework for Nonconvex Optimization via High-Order Moreau Envelope
This paper introduces ItsOPT, an inexact two-level smoothing optimization framework designed to find first-order critical points of nonsmooth and nonconvex functions. The framework consists of two levels of methodologies: at the upper level, a zeroth-, first-, or second-order method can be tailored to minimize a smooth approximation; at the lower level, the high-order proximal auxiliary problems are solved inexactly, generating an inexact oracle for the smooth function. As a smoothing technique, we introduce the high-order Moreau envelope (HOME) and study its fundamental properties under standard assumptions. Next, by combining a boosted high-order proximal-point algorithm (Boosted HiPPA) at the upper level with the inexact oracle from the lower level, we obtain a zeroth-order instance of ItsOPT. Global convergence rates are established under the Kurdyka–Łojasiewicz (KL) property of the cost and envelope functions, together with reasonable conditions on the accuracy of the proximal terms. Surprisingly, for any KL exponent [Formula: see text] of the original cost, setting the regularization order [Formula: see text] ensures that Boosted HiPPA converges linearly to a proximal fixed point. This is the first algorithm with this property for KL functions. Preliminary numerical experiments on a robust low-rank matrix recovery problem demonstrate the promising performance of the proposed algorithm, supporting our theoretical foundations.
- 2 November 2026
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Optimization
- Vol. 36 (4) , 2387-2416
ItsOPT: An Inexact Two-Level Smoothing Framework for Nonconvex Optimization via High-Order Moreau Envelope
This paper introduces ItsOPT, an inexact two-level smoothing optimization framework designed to find first-order critical points of nonsmooth and nonconvex functions. The framework consists of two levels of methodologies: at the upper level, a zeroth-, first-, or second-order method can be tailored to minimize a smooth approximation; at the lower level, the high-order proximal auxiliary problems are solved inexactly, generating an inexact oracle for the smooth function. As a smoothing technique, we introduce the high-order Moreau envelope (HOME) and study its fundamental properties under standard assumptions. Next, by combining a boosted high-order proximal-point algorithm (Boosted HiPPA) at the upper level with the inexact oracle from the lower level, we obtain a zeroth-order instance of ItsOPT. Global convergence rates are established under the Kurdyka–Łojasiewicz (KL) property of the cost and envelope functions, together with reasonable conditions on the accuracy of the proximal terms. Surprisingly, for any KL exponent [Formula: see text] of the original cost, setting the regularization order [Formula: see text] ensures that Boosted HiPPA converges linearly to a proximal fixed point. This is the first algorithm with this property for KL functions. Preliminary numerical experiments on a robust low-rank matrix recovery problem demonstrate the promising performance of the proposed algorithm, supporting our theoretical foundations.
- 28 October 2026
- Published by Springer Nature in Computational Optimization and Applications
- p. 1-48
ItsDEAL: inexact two-level smoothing descent algorithms for weakly convex optimization
- 28 October 2026
- Published by Springer Nature in Computational Optimization and Applications
- p. 1-48
ItsDEAL: inexact two-level smoothing descent algorithms for weakly convex optimization
- 7 September 2026
- Published by Springer Nature in Journal of Global Optimization
- p. 1-40
Projected subgradient methods for paraconvex optimization: Application to robust low-rank matrix recovery
- 7 September 2026
- Published by Springer Nature in Journal of Global Optimization
- p. 1-40
Projected subgradient methods for paraconvex optimization: Application to robust low-rank matrix recovery
- 29 June 2026
- Published by Springer Nature in Journal of Optimization Theory and Applications
- Vol. 210 (1) , 14
On Fundamental Properties of High-Order Forward-Backward Envelope
- 29 June 2026
- Published by Springer Nature in Journal of Optimization Theory and Applications
- Vol. 210 (1) , 14
On Fundamental Properties of High-Order Forward-Backward Envelope
- 12 December 2025
- Published by Springer Nature in Set-Valued and Variational Analysis
- Vol. 33 (4) , 47
Moreau Envelope and Proximal-Point Methods Under the Lens of High-Order Regularization
- 12 December 2025
- Published by Springer Nature in Set-Valued and Variational Analysis
- Vol. 33 (4) , 47
Moreau Envelope and Proximal-Point Methods Under the Lens of High-Order Regularization
- Open Access
Minimizing smooth Kurdyka-Łojasiewicz functions via generalized descent methods: Convergence rate and complexity
This paper addresses the generalized descent algorithm (DEAL) for minimizing smooth functions, which is analyzed under the Kurdyka-Łojasiewicz (KL) inequality. In particular, the suggested algorithm guarantees a sufficient decrease by adapting to the cost function's geometry. We leverage the KL property to establish the global convergence, convergence rates, and complexity. A particular focus is placed on the linear convergence of generalized descent methods. We show that the constant step-size and Armijo line search strategies along a generalized descent direction satisfy our generalized descent condition. Additionally, for nonsmooth functions by leveraging the smoothing techniques such as forward-backward and high-order Moreau envelopes, we show that the boosted proximal gradient method (BPGA) and the boosted high-order proximal-point (BPPA) methods are also specific cases of DEAL, respectively. It is notable that if the order of the high-order proximal term is chosen in a certain way (depending on the KL exponent), then the sequence generated by BPPA converges linearly for an arbitrary KL exponent. Our preliminary numerical experiments on inverse problems and LASSO demonstrate the efficiency of the proposed methods, validating our theoretical findings.
Open AccessMinimizing smooth Kurdyka-Łojasiewicz functions via generalized descent methods: Convergence rate and complexity
This paper addresses the generalized descent algorithm (DEAL) for minimizing smooth functions, which is analyzed under the Kurdyka-Łojasiewicz (KL) inequality. In particular, the suggested algorithm guarantees a sufficient decrease by adapting to the cost function's geometry. We leverage the KL property to establish the global convergence, convergence rates, and complexity. A particular focus is placed on the linear convergence of generalized descent methods. We show that the constant step-size and Armijo line search strategies along a generalized descent direction satisfy our generalized descent condition. Additionally, for nonsmooth functions by leveraging the smoothing techniques such as forward-backward and high-order Moreau envelopes, we show that the boosted proximal gradient method (BPGA) and the boosted high-order proximal-point (BPPA) methods are also specific cases of DEAL, respectively. It is notable that if the order of the high-order proximal term is chosen in a certain way (depending on the KL exponent), then the sequence generated by BPPA converges linearly for an arbitrary KL exponent. Our preliminary numerical experiments on inverse problems and LASSO demonstrate the efficiency of the proposed methods, validating our theoretical findings.
- Open Access
(Adaptive) Scaled gradient methods beyond locally Holder smoothness: Lyapunov analysis, convergence rate and complexity
This paper addresses the unconstrained minimization of smooth convex functions whose gradients are locally Holder continuous. Building on these results, we analyze the Scaled Gradient Algorithm (SGA) under local smoothness assumptions, proving its global convergence and iteration complexity. Furthermore, under local strong convexity and the Kurdyka-Lojasiewicz (KL) inequality, we establish linear convergence rates and provide explicit complexity bounds. In particular, we show that when the gradient is locally Lipschitz continuous, SGA attains linear convergence for any KL exponent. We then introduce and analyze an adaptive variant of SGA (AdaSGA), which automatically adjusts the scaling and step-size parameters. For this method, we show global convergence, and derive local linear rates under strong convexity.
Open Access(Adaptive) Scaled gradient methods beyond locally Holder smoothness: Lyapunov analysis, convergence rate and complexity
This paper addresses the unconstrained minimization of smooth convex functions whose gradients are locally Holder continuous. Building on these results, we analyze the Scaled Gradient Algorithm (SGA) under local smoothness assumptions, proving its global convergence and iteration complexity. Furthermore, under local strong convexity and the Kurdyka-Lojasiewicz (KL) inequality, we establish linear convergence rates and provide explicit complexity bounds. In particular, we show that when the gradient is locally Lipschitz continuous, SGA attains linear convergence for any KL exponent. We then introduce and analyze an adaptive variant of SGA (AdaSGA), which automatically adjusts the scaling and step-size parameters. For this method, we show global convergence, and derive local linear rates under strong convexity.
- Open Access
First-order majorization-minimization meets high-order majorant: Boosted inexact high-order forward-backward method
This paper introduces a first-order majorization-minimization framework based on a high-order majorant for continuous functions, incorporating a non-quadratic regularization term of degree $p>1$. Notably, it is shown to be valid if and only if the function is $p$-paraconcave, thus extending beyond Lipschitz and Hölder gradient continuity for $p \in (1,2]$, and implying concavity for $p>2$. In the smooth setting, this majorant recovers a variant of the classical descent lemma with quadratic regularization. Building on this foundation, we develop a high-order inexact forward-backward algorithm (HiFBA) and its line-search-accelerated variant, named Boosted HiFBA. For convergence analysis, we introduce a high-order forward-backward envelope (HiFBE), which serves as a Lyapunov function. We establish subsequential convergence under suitable inexactness conditions, and we prove global convergence with linear rates for functions satisfying the Kurdyka-Łojasiewicz inequality. Our preliminary experiments on linear inverse problems and regularized nonnegative matrix factorization highlight the efficiency of HiFBA and its boosted variant, demonstrating their potential for solving challenging nonconvex optimization problems.Open AccessFirst-order majorization-minimization meets high-order majorant: Boosted inexact high-order forward-backward method
This paper introduces a first-order majorization-minimization framework based on a high-order majorant for continuous functions, incorporating a non-quadratic regularization term of degree $p>1$. Notably, it is shown to be valid if and only if the function is $p$-paraconcave, thus extending beyond Lipschitz and Hölder gradient continuity for $p \in (1,2]$, and implying concavity for $p>2$. In the smooth setting, this majorant recovers a variant of the classical descent lemma with quadratic regularization. Building on this foundation, we develop a high-order inexact forward-backward algorithm (HiFBA) and its line-search-accelerated variant, named Boosted HiFBA. For convergence analysis, we introduce a high-order forward-backward envelope (HiFBE), which serves as a Lyapunov function. We establish subsequential convergence under suitable inexactness conditions, and we prove global convergence with linear rates for functions satisfying the Kurdyka-Łojasiewicz inequality. Our preliminary experiments on linear inverse problems and regularized nonnegative matrix factorization highlight the efficiency of HiFBA and its boosted variant, demonstrating their potential for solving challenging nonconvex optimization problems. - Open Access
Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization
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 curvilinear linesearch method. These developments are grounded in the forward-backward envelope (FBE), for which we analyze the local second-order differentiability around critical points and establish a novel equivalence between its second-order stationary points and those of the original objective. We show that the proposed algorithms converge to second-order stationary points of the FBE under a mild local smoothness condition on the proximal mapping of the nonsmooth term. Notably, for \( \C^2 \)-partly smooth functions, this condition holds under a standard strict complementarity assumption. To the best of our knowledge, these are the first second-order algorithms that provably escape nonsmooth strict saddle points of composite nonconvex optimization, regardless of the initialization. Our preliminary numerical experiments show promising performance of the developed methods, validating our theoretical foundations.Open AccessSecond-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization
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 curvilinear linesearch method. These developments are grounded in the forward-backward envelope (FBE), for which we analyze the local second-order differentiability around critical points and establish a novel equivalence between its second-order stationary points and those of the original objective. We show that the proposed algorithms converge to second-order stationary points of the FBE under a mild local smoothness condition on the proximal mapping of the nonsmooth term. Notably, for \( \C^2 \)-partly smooth functions, this condition holds under a standard strict complementarity assumption. To the best of our knowledge, these are the first second-order algorithms that provably escape nonsmooth strict saddle points of composite nonconvex optimization, regardless of the initialization. Our preliminary numerical experiments show promising performance of the developed methods, validating our theoretical foundations.