Heteroscedastic Uncertainty

Heteroscedastic Uncertainty is a type of uncertainty estimation in which the variability of model prediction errors is explicitly dependent on the input data, distinguishing it from homoscedastic uncertainty by allowing the noise level to vary across different regions of the input space.

87

Publications

3.4K

Citations

252

Authors

147

Institutions

Publications per year

2017–2026

38

Authors

252

  1. FP
    Francesca Pianosi

    University of Bristol, United Kingdom

    2 publications · 104 citations

    2

    h-index

  2. AB
    Alberto Bizzi

    Fondazione IRCCS Istituto Neurologico Carlo Besta, Italy

    2 publications · 142 citations

    2

    h-index

  3. AG
    Aurobrata Ghosh

    Institut national de recherche en sciences et technologies du numérique, France

    2 publications · 142 citations

    2

    h-index

  4. DC
    Dorin Comaniciu

    Siemens (United States), United States

    2 publications · 220 citations

    2

    h-index

  5. SN
    Stamatios N. Sotiropoulos

    Wellcome Centre for Integrative Neuroimaging, United Kingdom

    2 publications · 142 citations

    2

    h-index

1–5 of 252

Venues

  1. arXiv (Cornell University)

    Repository · 9 publications · 251 citations

    9

    h-index

  2. Water Resources Research

    6 publications · 391 citations

    6

    h-index

  3. SSRN Electronic Journal

    Repository · 3 publications · 59 citations

    3

    h-index

  4. Industrial & Engineering Chemistry Research

    3 publications · 69 citations

    3

    h-index

  5. 2

    h-index

1–5