Online Convex Optimization

Online Convex Optimization is an online learning framework in which a learner sequentially selects points from a fixed convex set and incurs losses defined by a sequence of convex functions, with the objective of minimizing regret relative to the best fixed decision in hindsight.

502

Publications

122.4K

Citations

929

Authors

334

Institutions

Publications per year

2017–2026

266

Authors

929

  1. EH
    Elad Hazan

    Princeton University, United States

    29 publications · 11.1K citations

    22

    h-index

  2. AW
    Adam Wierman

    California Institute of Technology, United States

    15 publications · 483 citations

    14

    h-index

  3. JA
    Jacob Abernethy

    University of California, Berkeley, United States

    10 publications · 664 citations

    10

    h-index

  4. AR
    Alexander Rakhlin

    University of Pennsylvania, United States

    10 publications · 796 citations

    10

    h-index

  5. DZ
    Ding‐Xuan Zhou

    City University of Hong Kong, Hong Kong SAR China

    10 publications · 344 citations

    10

    h-index

1–5 of 929

Venues

  1. arXiv (Cornell University)

    Repository · 105 publications · 3.4K citations

    32

    h-index

  2. IEEE Transactions on Automatic Control

    21 publications · 1.2K citations

    20

    h-index

  3. IEEE Transactions on Signal Processing

    9 publications · 982 citations

    10

    h-index

  4. Neural Information Processing Systems

    Conference · 8 publications · 505 citations

    8

    h-index

  5. Automatica

    5 publications · 113 citations

    7

    h-index

1–5