Login / Signup

Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation.

Alain DurmusEric MoulinesAlexey NaumovSergey Samsonov
Published in: CoRR (2022)
Keyphrases
  • stochastic approximation
  • monte carlo
  • lower bound
  • upper bound
  • probability distribution
  • approximation methods
  • least squares
  • neural network
  • reinforcement learning