Gradient-based Optimization

Gradient-Based Optimization is a mathematical optimization method that iteratively minimizes or maximizes an objective function by utilizing the gradient information to determine the direction of steepest descent or ascent, distinguishing itself from derivative-free or heuristic approaches through its reliance on first-order or higher-order derivative data.

7.6K

Publications

776.3K

Citations

12.3K

Authors

2.7K

Institutions

Publications per year

2017–2026

3.3K

Authors

12.3K

  1. MI
    Michael I. Jordan

    University of California, Berkeley, United States

    36 publications · 3.1K citations

    28

    h-index

  2. PK
    Poom Kumam

    King Mongkut's University of Technology Thonburi, Thailand

    49 publications · 1.5K citations

    26

    h-index

  3. JN
    Jorge Nocedal

    Northwestern University, United States

    31 publications · 15.4K citations

    25

    h-index

  4. NA
    Neculai Andrei

    National Institute for Research and Development in Informatics - ICI Bucharest, Romania

    31 publications · 1.6K citations

    25

    h-index

  5. PR
    Peter Richtárik

    University of Edinburgh, United Kingdom

    51 publications · 2.9K citations

    24

    h-index

1–5 of 12.3K

Venues

  1. arXiv (Cornell University)

    Repository · 1.2K publications · 95.1K citations

    114

    h-index

  2. SIAM Journal on Optimization

    293 publications · 33.4K citations

    96

    h-index

  3. Mathematical Programming

    164 publications · 25.9K citations

    70

    h-index

  4. Journal of Optimization Theory and Applications

    201 publications · 17.4K citations

    60

    h-index

  5. IEEE Transactions on Neural Networks

    69 publications · 16.1K citations

    48

    h-index

1–5