Rate of convergence of the Nesterov accelerated gradient method in the subcritical case α≤ 3

H Attouch, Z Chbani, H Riahi - ESAIM: Control, Optimisation and …, 2019 - esaim-cocv.org
In a Hilbert space setting ℋ, given Φ: ℋ→ ℝ a convex continuously differentiable function,
and α a positive parameter, we consider the inertial dynamic system with Asymptotic …

Combining fast inertial dynamics for convex optimization with Tikhonov regularization

H Attouch, Z Chbani, H Riahi - Journal of Mathematical Analysis and …, 2018 - Elsevier
In a Hilbert space setting H, we study the convergence properties as t→+∞ of the
trajectories of the second-order differential equation (AVD) α, ϵ x¨(t)+ α tx˙(t)+∇ Φ (x (t))+ ϵ …

Optimal convergence rates for Nesterov acceleration

JF Aujol, C Dossal, A Rondepierre - SIAM Journal on Optimization, 2019 - SIAM
In this paper, we study the behavior of solutions of the ODE associated to Nesterov
acceleration. It is well-known since the pioneering work of Nesterov that the rate of …

First-order optimization algorithms via inertial systems with Hessian driven damping

H Attouch, Z Chbani, J Fadili, H Riahi - Mathematical Programming, 2022 - Springer
In a Hilbert space setting, for convex optimization, we analyze the convergence rate of a
class of first-order algorithms involving inertial features. They can be interpreted as discrete …

Asymptotic stabilization of inertial gradient dynamics with time-dependent viscosity

H Attouch, A Cabot - Journal of Differential Equations, 2017 - Elsevier
In a Hilbert space H, we study the asymptotic behavior, as time variable t goes to+∞, of
nonautonomous gradient-like inertial dynamics, with a time-dependent viscosity coefficient …

Convergence of iterates for first-order optimization algorithms with inertia and Hessian driven damping

H Attouch, Z Chbani, J Fadili, H Riahi - Optimization, 2023 - Taylor & Francis
In a Hilbert space setting, for convex optimization, we show the convergence of the iterates
to optimal solutions for a class of accelerated first-order algorithms. They can be interpreted …

Newton-like inertial dynamics and proximal algorithms governed by maximally monotone operators

H Attouch, SC László - SIAM Journal on Optimization, 2020 - SIAM
The introduction of the Hessian damping in the continuous version of Nesterov's accelerated
gradient method provides, by temporal discretization, fast proximal gradient algorithms …

Convergence rates of inertial forward-backward algorithms

H Attouch, A Cabot - SIAM Journal on Optimization, 2018 - SIAM
In a Hilbert space \mathcalH, assuming (\alpha_k) a general sequence of nonnegative
numbers, we analyze the convergence properties of the inertial forward-backward algorithm …

The connection between nesterov's accelerated methods and halpern fixed-point iterations

Q Tran-Dinh - arXiv preprint arXiv:2203.04869, 2022 - arxiv.org
We derive a direct connection between Nesterov's accelerated first-order algorithm and the
Halpern fixed-point iteration scheme for approximating a solution of a co-coercive equation …

Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity

H Attouch, Z Chbani, J Peypouquet… - Mathematical Programming, 2018 - Springer
In a Hilbert space setting H, we study the fast convergence properties as t→+∞ of the
trajectories of the second-order differential equation x¨(t)+ α tx˙(t)+∇ Φ (x (t))= g (t), where∇ …