Hessian informed mirror descent

DOI10.1007/s10915-022-01933-5zbMath1498.65102arXiv2106.13477OpenAlexW3176115357MaRDI QIDQ2162317

Li Wang, Ming Yan

Publication date: 5 August 2022

Published in: Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2106.13477

zbMATH Keywords

Wasserstein gradient flowvariable metricmirror descentdegenerate mobility

Mathematics Subject Classification ID

Convex programming (90C25) Numerical optimization and variational techniques (65K10)

Related Items

Approximate Newton Policy Gradient Algorithms, Geometry and convergence of natural policy gradient methods, Structure Preserving Primal Dual Methods for Gradient Flows with Nonlinear Mobility Transport Distances

Cites Work

• Unnamed Item
• Unnamed Item
• A nonlocal continuum model for biological aggregation
• Local existence of weak solutions to kinetic models of granular media
• Variable metric forward-backward algorithm for minimizing the sum of a differentiable function and a convex function
• Fisher information regularization schemes for Wasserstein gradient flows
• Traveling bands of chemotactic bacteria: a theoretical analysis
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Kinetic equilibration rates for granular media and related equations: entropy dissipation and mass transportation estimates
• Primal dual methods for Wasserstein gradient flows
• Mirror descent algorithms for minimizing interacting free energy
• Convergence to equilibrium for the Cahn-Hilliard equation with a logarithmic free energy
• Proximal Newton-Type Methods for Minimizing Composite Functions
• Particle, kinetic, and hydrodynamic models of swarming
• Scaling algorithms for unbalanced optimal transport problems
• An augmented Lagrangian approach to Wasserstein gradient flows and applications
• Entropic Approximation of Wasserstein Gradient Flows
• Inpainting of Binary Images Using the Cahn–Hilliard Equation
• The Variational Formulation of the Fokker--Planck Equation
• A multiphase Cahn–Hilliard–Darcy model for tumour growth with necrosis
• A Characterization of Superlinear Convergence and Its Application to Quasi-Newton Methods
• On the Cahn–Hilliard Equation with Degenerate Mobility
• Finite Element Approximation of the Cahn--Hilliard Equation with Degenerate Mobility
• A mean field view of the landscape of two-layer neural networks
• The back-and-forth method for Wasserstein gradient flows
• Aggregation-Diffusion Equations: Dynamics, Asymptotics, and Singular Limits
• Phase Transitions in a Kinetic Flocking Model of Cucker--Smale Type