Langevin dynamics based algorithm e-TH$\varepsilon$O POULA for stochastic optimization problems with discontinuous stochastic gradient

Documenti analoghi

• Non-asymptotic convergence analysis of the stochastic gradient Hamiltonian Monte Carlo algorithm with discontinuous stochastic gradient with applications to training of ReLU neural networks
  di: Liang, Luxu, et al.
  Pubblicazione: (2024)
• Provably convergent stochastic fixed-point algorithm for free-support Wasserstein barycenter of continuous non-parametric measures
  di: Chen, Zeyi, et al.
  Pubblicazione: (2025)
• Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
  di: Lim, Dong-Young, et al.
  Pubblicazione: (2021)
• Numerical method for approximately optimal solutions of two-stage distributionally robust optimization with marginal constraints
  di: Neufeld, Ariel, et al.
  Pubblicazione: (2022)
• Numerical method for feasible and approximately optimal solutions of multi-marginal optimal transport beyond discrete measures
  di: Neufeld, Ariel, et al.
  Pubblicazione: (2022)