Mini-batch Gradient Descent

Mini-Batch Gradient Descent is a gradient-based optimization algorithm that, as a variant of stochastic gradient descent, computes parameter updates using the average gradient of a small, randomly sampled subset of training data—termed a mini-batch—thereby balancing the computational efficiency of stochastic updates with the stability of batch gradient descent.

197

Publications

14.3K

Citations

599

Authors

242

Institutions

Publications per year

2017–2026

148

Variants

Mini-batch Sgd

Authors

599

  1. MT
    Martin Takáč

    Lehigh University, United States

    7 publications · 732 citations

    7

    h-index

  2. LM
    Lam M. Nguyen

    University of North Carolina at Chapel Hill, United States

    5 publications · 180 citations

    5

    h-index

  3. PR
    Peter Richtárik

    University of Edinburgh, United Kingdom

    4 publications · 458 citations

    4

    h-index

  4. ZA
    Zeyuan Allen-Zhu

    Princeton University, United States

    4 publications · 244 citations

    4

    h-index

  5. MB
    Mikhail Belkin

    The Ohio State University, United States

    4 publications · 201 citations

    4

    h-index

1–5 of 599

Venues

  1. arXiv (Cornell University)

    Repository · 63 publications · 7.1K citations

    29

    h-index

  2. Neurocomputing

    8 publications · 185 citations

    7

    h-index

  3. Neural Networks

    5 publications · 577 citations

    5

    h-index

  4. IEEE Access

    5 publications · 210 citations

    5

    h-index

  5. IEEE Transactions on Fuzzy Systems

    TFS · 4 publications · 374 citations

    4

    h-index

1–5