Hessian Riemannian Gradient Flows in Convex Programming

DOI10.1137/S0363012902419977zbMath1077.34050arXiv1811.10331OpenAlexW3103305945WikidataQ115246809 ScholiaQ115246809MaRDI QIDQ4652545

Olivier Brahic, Felipe Alvarez, Jérôme Bolte

Publication date: 28 February 2005

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.10331

zbMATH Keywords

global convergenceexistencegradient flowLyapunov functionalBregman distanceLegendre transform coordinatesconvex and linear programmingHessian Riemannian metricLagrange and Hamilton equationsLegendre-type convex functionquasi-convex minimization

Mathematics Subject Classification ID

Convex programming (90C25) Initial value problems, existence, uniqueness, continuous dependence and continuation of solutions to ordinary differential equations (34A12) Asymptotic properties of solutions to ordinary differential equations (34D05) Ordinary differential equations and systems on manifolds (34C40)

Related Items

Geometry of matrix decompositions seen through optimal transport and information geometry ⋮ First-order geometric multilevel optimization for discrete tomography ⋮ Replicator dynamics: old and new ⋮ Riemannian game dynamics ⋮ Stochastic mirror descent dynamics and their convergence in monotone variational inequalities ⋮ Penalty-Regulated Dynamics and Robust Learning Procedures in Games ⋮ Physarum-inspired multi-commodity flow dynamics ⋮ An inexact proximal method for quasiconvex minimization ⋮ Full convergence of the proximal point method for quasiconvex functions on Hadamard manifolds ⋮ Inertial Game Dynamics and Applications to Constrained Optimization ⋮ Unnamed Item ⋮ Gradient Flows, Second-Order Gradient Systems and Convexity ⋮ An alternative to EM for Gaussian mixture models: batch and stochastic Riemannian optimization ⋮ Fenchel conjugate via Busemann function on Hadamard manifolds ⋮ Time-varying distributed optimization problem with inequality constraints ⋮ No-regret algorithms in on-line learning, games and convex optimization ⋮ Unnamed Item ⋮ Conformal mirror descent with logarithmic divergences ⋮ Geometry and convergence of natural policy gradient methods ⋮ Continuous time learning algorithms in optimization and game theory ⋮ A Geodesic Interior-Point Method for Linear Optimization over Symmetric Cones ⋮ An extension of proximal methods for quasiconvex minimization on the nonnegative orthant ⋮ First-order methods for convex optimization ⋮ On the Convergence of Gradient-Like Flows with Noisy Gradient Input ⋮ Sign projected gradient flow: a continuous-time approach to convex optimization with linear equality constraints ⋮ Proximal point method for minimizing quasiconvex locally Lipschitz functions on Hadamard manifolds ⋮ Learning in games with continuous action sets and unknown payoff functions ⋮ Markovian traffic equilibrium ⋮ Legendre transform and applications to finite and infinite optimization ⋮ Second-Order Dynamics with Hessian-Driven Damping for Linearly Constrained Convex Minimization ⋮ Singular Riemannian barrier methods and gradient-projection dynamical systems for constrained optimization ⋮ Principal Subspace Flows Via Mechanical Systems on Grassmann Manifolds ⋮ A Laplacian approach to \(\ell_1\)-norm minimization ⋮ Central paths in semidefinite programming, generalized proximal-point method and Cauchy trajectories in Riemannian manifolds ⋮ Hessian Barrier Algorithms for Linearly Constrained Optimization Problems ⋮ Learning in Games via Reinforcement and Regularization ⋮ The Hessian Riemannian flow and Newton’s method for effective Hamiltonians and Mather measures ⋮ Curiosities and counterexamples in smooth convex optimization ⋮ Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates

This page was built for publication: Hessian Riemannian Gradient Flows in Convex Programming