An error bound-based convergence analysis framework for a class of randomized algorithms

Documenti analoghi

• Variance Reduced Random Relaxed Projection Method for Constrained Finite-sum Minimization Problems
  di: Yang, Zhichun, et al.
  Pubblicazione: (2022)
• Subdifferentially polynomially bounded functions and Gaussian smoothing-based zeroth-order optimization
  di: Lei, Ming, et al.
  Pubblicazione: (2024)
• A nonmonotone extrapolated proximal gradient-subgradient algorithm beyond global Lipschitz gradient continuity
  di: Yang, Lei, et al.
  Pubblicazione: (2025)
• An MILP-Based Solution Scheme for Factored and Robust Factored Markov Decision Processes
  di: Liu, Huikang, et al.
  Pubblicazione: (2024)
• Why does the two-timescale Q-learning converge to different mean field solutions? A unified convergence analysis
  di: An, Jing, et al.
  Pubblicazione: (2024)