Non-asymptotic convergence analysis of the stochastic gradient Hamiltonian Monte Carlo algorithm with discontinuous stochastic gradient with applications to training of ReLU neural networks

Documenti analoghi

• Langevin dynamics based algorithm e-TH$\varepsilon$O POULA for stochastic optimization problems with discontinuous stochastic gradient
  di: Lim, Dong-Young, et al.
  Pubblicazione: (2022)
• Provably convergent stochastic fixed-point algorithm for free-support Wasserstein barycenter of continuous non-parametric measures
  di: Chen, Zeyi, et al.
  Pubblicazione: (2025)
• Non-asymptotic convergence bounds for modified tamed unadjusted Langevin algorithm in non-convex setting
  di: Neufeld, Ariel, et al.
  Pubblicazione: (2022)
• Multilevel Picard approximations and deep neural networks with ReLU, leaky ReLU, and softplus activation overcome the curse of dimensionality when approximating semilinear parabolic partial differential equations in $L^p$-sense
  di: Neufeld, Ariel, et al.
  Pubblicazione: (2024)
• Deep ReLU neural networks overcome the curse of dimensionality when approximating semilinear partial integro-differential equations
  di: Neufeld, Ariel, et al.
  Pubblicazione: (2023)