Approximation Methods which Converge with Probability one

By J. Blum. 1954

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming (2006, background): “Robbins and Monro (1951) describes a more general version of this procedure, which is proved to be convergent in Blum (1954a) .”
SEQUENTIAL ANALYSIS: SOME CLASSICAL PROBLEMS AND NEW CHALLENGES (2001, background): “Blum (1954) proved a.s. convergence of the Kiefer-Wolfowitz scheme to the maximizer of M under certain assumptions on M, (1) n and (2) n .”
Optimal Linear Combination of Neural Networks for Improving Classification Performance (2000, methodology): “From the theory of stochastic approximation [ 3 ], it is guaranteed that OtU will converge to at least a local optimum solution if OtU satisfies the following conditions:”