2 citations · 3 across the 12 of their papers we have counts for
13 papers
Stochastic convergence of parallel asynchronous adaptive first-order methods
Serge Gratton, Philippe L. Toint
A new class of asynchronous adaptive first-order optimization methods is introduced, comprising asynchronous variants of several popular algorithms. Versions of these methods using…
A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad and Muon
S. Gratton, Ph. L. Toint
A unified framework for first-order optimization algorithms fornonconvex unconstrained optimization is proposed that uses adaptivelypreconditioned gradients and includes popular me…
An objective-function-free algorithm for nonconvex stochastic optimization with deterministic equality and inequality constraints
S. Gratton, Ph. L. Toint
An algorithm is proposed for solving optimization problems with stochastic objective and deterministic equality and inequality constraints. This algorithm is objective-function-fre…
An objective-function-free algorithm for general smooth constrained optimization
S. Bellavia, S. Gratton, B. Morini +1
A new algorithm for smooth constrained optimization is proposed that never computes the value of the problem's objective function and that handles both equality and inequality cons…
Iteration complexity of the Difference-of-Convex Algorithm for unconstrained optimization: a simple proof
Serge Gratton, Philippe L. Toint
We propose a simple proof of the worst-case iteration complexity for the Difference of Convex functions Algorithm (DCA) for unconstrained minimization, showing that the global rate…
ADSWITCH: A Simple First-Order Algorithm for Full-Rank Equality Constrained Optimization
Serge Gratton, Philippe L. Toint
A very simple first-order algorithm is proposed for solving nonlinear optimization problems with deterministic nonlinear equality constraints. This algorithm adaptively selects ste…
Recursive Bound-Constrained AdaGrad with Applications to Multilevel and Domain Decomposition Minimization
Serge Gratton, Alena Kopaničáková, Philippe Toint
Two OFFO (Objective-Function Free Optimization) noise tolerant algorithms are presented that handle bound constraints, inexact gradients and use second-order information when avail…
A Fast Newton Method Under Local Lipschitz Smoothness
Serge Gratton, Sadok Jerad, Philippe L. Toint
A new, fast second-order method is proposed that achieves the optimal complexity to obtain first-order -stationary points. Crucially,…
Refining asymptotic complexity bounds for nonconvex optimization methods, including why steepest descent is rather than
Serge Gratton, Chee-Khian Sim, Philippe L. Toint
We revisit the standard ``telescoping sum'' argument ubiquitous in the final steps of analyzing evaluation complexity of algorithms for smooth nonconvex optimization, and obtain a…
A Stochastic Objective-Function-Free Adaptive Regularization Method with Optimal Complexity
Serge Gratton, Sadok Jerad, Philippe L. Toint
A fully stochastic second-order adaptive-regularization method for unconstrained nonconvex optimization is presented which never computes the objective-function value, but yet achi…
Complexity of Adagrad and other first-order methods for nonconvex optimization problems with bounds constraints
Serge Gratton, Sadok Jerad, Philippe L. Toint
A parametric class of trust-region algorithms for constrained nonconvex optimization is analyzed, where the objective function is never computed. By defining appropriate first-orde…
An optimally fast objective-function-free minimization algorithm using random subspaces
S. Bellavia, S. Gratton, B. Morini +1
An algorithm for unconstrained non-convex optimization is described, which does not evaluate the objective function and in which minimization is carried out, at each iteration, wit…
Complexity of a Class of First-Order Objective-Function-Free Optimization Algorithms
S. Gratton, S. Jerad, Ph. L. Toint
A parametric class of trust-region algorithms for unconstrained nonconvex optimization is considered where the value of the objective function is never computed. The class contains…