Stochastic Approximation
Overview
Stochastic approximation studies how repeated updates based on noisy samples can find solutions to optimization, root-finding, and fixed-point problems, including those in reinforcement learning. Common approaches include Polyak–Ruppert averaging, two-time-scale updates, variance reduction, and Lyapunov or Poisson-equation analyses to control noise and dependence. Current work develops finite-time convergence and uncertainty guarantees for settings such as Markovian data, heavy-tailed noise, and asynchronous updates. A central challenge is to obtain sharp, reliable rates without restrictive assumptions on smoothness, stability, or noise.
Latest papers
83 papers7 papers in the last four weeks, down 56% on the four weeks before. 0.1% of all new papers.