Stochastic Approximation

Stochastic Approximation is a recursive optimization algorithm that belongs to the class of iterative methods for solving root-finding or minimization problems, distinguished by its use of noisy or stochastic observations to approximate gradients or function values in environments with uncertainty.

1.7K

Publications

112.9K

Citations

2.6K

Authors

986

Institutions

Publications per year

2017–2026

325

Authors

2.6K

  1. JC
    James C. Spall

    Johns Hopkins University Applied Physics Laboratory, United States

    39 publications · 5.4K citations

    24

    h-index

  2. HJ
    Harold J. Kushner

    Brown University, United States

    31 publications · 3K citations

    22

    h-index

  3. GY
    George Yin

    Wayne State University, United States

    22 publications · 847 citations

    17

    h-index

  4. VK
    Vikram Krishnamurthy

    University of British Columbia, Canada

    22 publications · 1.2K citations

    17

    h-index

  5. MC
    Michael C. Fu

    University of Maryland, College Park, United States

    20 publications · 1.5K citations

    16

    h-index

1–5 of 2.6K

Venues

  1. IEEE Transactions on Automatic Control

    114 publications · 11.1K citations

    47

    h-index

  2. arXiv (Cornell University)

    Repository · 87 publications · 8K citations

    29

    h-index

  3. SIAM Journal on Control and Optimization

    41 publications · 5.4K citations

    28

    h-index

  4. IEEE Transactions on Signal Processing

    28 publications · 2.6K citations

    22

    h-index

  5. IEEE Transactions on Information Theory

    31 publications · 1.7K citations

    22

    h-index

1–5