A Stochastic Approximation Method

@inproceedings{Robbins2007ASA,
  title={A Stochastic Approximation Method},
  author={Herbert E. Robbins},
  year={2007}
}
  • Herbert E. Robbins
  • Published 2007
  • Mathematics
  • Let M(x) denote the expected value at level x of the response to a certain experiment. M(x) is assumed to be a monotone function of x but is unknown tot he experiment, and it is desire to find the solution x=0 of the equation M(x) = a, where x is a given constant. we give a method for making successive experiments at levels x1, x2,... in such a way that x, will tend to 0 in probability. 

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 3,131 CITATIONS

    Knowledge base completion by learning pairwise-interaction differentiated embeddings

    VIEW 4 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Progressive Identification of True Labels for Partial-Label Learning

    VIEW 6 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    An Adaptive and Momental Bound Method for Stochastic Learning

    VIEW 13 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Diversely Stale Parameters for Efficient Training of CNNs

    VIEW 7 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Generalized Inner Loop Meta-Learning

    VIEW 11 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization

    VIEW 27 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Improving Scalability of Parallel CNN Training by Adjusting Mini-Batch Size at Run-Time

    VIEW 11 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    1959
    2019

    CITATION STATISTICS

    • 402 Highly Influenced Citations

    • Averaged 469 Citations per year from 2017 through 2019

    • 46% Increase in citations per year in 2019 over 2018