Rate of convergence of the Nesterov accelerated gradient method in the subcritical case α≤ 3
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 …
and α a positive parameter, we consider the inertial dynamic system with Asymptotic …
Combining fast inertial dynamics for convex optimization with Tikhonov regularization
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 …
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
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 …
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
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 …
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 …
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
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 …
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
The introduction of the Hessian damping in the continuous version of Nesterov's accelerated
gradient method provides, by temporal discretization, fast proximal gradient algorithms …
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 …
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 …
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
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∇ …
trajectories of the second-order differential equation x¨(t)+ α tx˙(t)+∇ Φ (x (t))= g (t), where∇ …