Stochastic Gradient Leimkuhler-Matthews Integrator with Second Order Discretization Error
math.NA, cs.NA, math.PR
Submitted: 2026-10-17
Updated: 2026-11-04
Code: https://github.com/xuda-ye-math/Poisson-SGLM
Terminology
Sources
- Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin
- Sharp convergence rates for Langevin dynamics in the nonconvex setting
- Multilevel Monte Carlo for Scalable Bayesian Computations
- Mean square error analysis of stochastic gradient and variance-reduced sampling algorithms
- Langevin Markov Chain Monte Carlo with stochastic gradients
- The True Cost of Stochastic Gradient Langevin Dynamics
- Theoretical guarantees for stochastic gradient sampling methods via Gaussian convolution inequalities
- Random Reshuffling for Stochastic Gradient Langevin Dynamics
- Mean Square Error Analysis of Stochastic Runge-Kutta Integrators
Related papers
- Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
- A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
- Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)
- Operator learning meets inverse problems: A probabilistic perspective
- Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
- Windowed thinning and query complexity for the bouncy particle and Zigzag samplers