On dissipative symplectic integration with applications to gradient-based optimization

DOI10.1088/1742-5468/abf5d4zbMath1489.82010arXiv2004.06840OpenAlexW3184876224MaRDI QIDQ3382316

No author found.

Publication date: 21 September 2021

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2004.06840

zbMATH Keywords

analysis of algorithmsmachine learningoptimization under uncertainty

Mathematics Subject Classification ID

Lattice systems (Ising, dimer, Potts, etc.) and systems on graphs arising in equilibrium statistical mechanics (82B20) Numerical methods for Hamiltonian systems including symplectic integrators (65P10) Numerical integration (65D30) Methods of reduced gradient type (90C52) Discretization methods and integrators (symplectic, variational, geometric, etc.) for dynamical systems (37M15) Statistical mechanics of magnetic materials (82D40) Monte Carlo methods applied to problems in statistical mechanics (82M31)

Related Items

Time-adaptive Lagrangian variational integrators for accelerated optimization ⋮ Bregman dynamics, contact transformations and convex optimization ⋮ Lagrangian and Hamiltonian dynamics for probabilities on the statistical bundle ⋮ Unnamed Item ⋮ A control-theoretic perspective on optimal high-order optimization ⋮ Rényi relative entropy from homogeneous Kullback-Leibler divergence Lagrangian

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Symplectic geometry: an introduction based on the seminar in Bern, 1992
• The life-span of backward error analysis for numerical integrators
• Exponential integrators preserving local conservation laws of PDEs with time-dependent damping/driving forces
• Families of high-order composition methods
• On the Hamiltonian interpolation of near-to-the-identity symplectic mappings with application to symplectic integration algorithms
• Second order conformal symplectic schemes for damped Hamiltonian systems
• Mathematical aspects of classical and celestial mechanics. Transl. from the Russian by E. Khukhro.
• Multi-conformal-symplectic PDEs and discretizations
• A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights
• Training Products of Experts by Minimizing Contrastive Divergence
• Simulating Hamiltonian Dynamics
• Backward Error Analysis for Numerical Integrators
• Solving the quantum many-body problem with artificial neural networks
• A variational perspective on accelerated methods in optimization
• Structure-preserving integrators for dissipative systems based on reversible– irreversible splitting
• Geometric integrators for ODEs
• Geometric Numerical Integration
• Some methods of speeding up the convergence of iteration methods
• Conformal symplectic and relativistic optimization
• Conformal Hamiltonian systems
• Probing magneto-elastic phenomena through an effective spin-Bath coupling model