DYNAMICAL, SYMPLECTIC AND STOCHASTIC PERSPECTIVES ON GRADIENT-BASED OPTIMIZATION

DOI10.1142/9789813272880_0022OpenAlexW2972507487MaRDI QIDQ5121993

Michael I. Jordan

Publication date: 22 September 2020

Published in: Proceedings of the International Congress of Mathematicians (ICM 2018) (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/9789813272880_0022

Mathematics Subject Classification ID

Convex programming (90C25) Nonconvex programming, global optimization (90C26) Numerical optimization and variational techniques (65K10) Discretization methods and integrators (symplectic, variational, geometric, etc.) for dynamical systems (37M15) Numerical methods in optimal control (49M99)

Related Items (8)

A New Likelihood Ratio Method for Training Artificial Neural Networks ⋮ Practical perspectives on symplectic accelerated optimization ⋮ Time-adaptive Lagrangian variational integrators for accelerated optimization ⋮ Asymptotic analysis of a structure-preserving integrator for damped Hamiltonian systems ⋮ Convergence Rates of Inertial Primal-Dual Dynamical Methods for Separable Convex Optimization Problems ⋮ Generalization of the gradient method with fractional order gradient direction ⋮ An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications ⋮ Fast primal-dual algorithm via dynamical system for a linearly constrained convex optimization problem

This page was built for publication: DYNAMICAL, SYMPLECTIC AND STOCHASTIC PERSPECTIVES ON GRADIENT-BASED OPTIMIZATION