Concepedia

Interpolation Threshold

Interpolation Threshold is a phenomenon in statistical learning theory wherein the generalization error of a model exhibits a non-monotonic behavior as a function of model complexity, specifically transitioning from overfitting to interpolation and back due to the onset of double descent, marking the point beyond which increasing model capacity allows perfect fitting of training data without necessarily worsening test performance.

12

Publications

747

Citations

21

Authors

16

Institutions

Publications per year

2017–2026

9

Parents

Publications

12

The generalization error of random features regression: Precise asymptotics and double descent curve

Andrea Montanari · arXiv (Cornell University) · 2019 · 248 citations · Full text

, , +13

The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve

Andrea Montanari · Communications on Pure and Applied Mathematics · 2021 · 191 citations

, , +11

Generalisation error in learning with random features and the hidden manifold model*

Federica Gerace, Bruno Loureiro, Florent Krząkała et al. · Journal of Statistical Mechanics Theory and Experiment · 2021 · 79 citations · Full text

, , +17

Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime

Stéphane d’Ascoli, Maria Refinetti, Giulio Biroli et al. · arXiv (Cornell University) · 2020 · 53 citations · Full text

, , +14

Problems of Further Development of the Group Method of Data Handling Algorithms. Part I

A. G. Ivakhnenko, G. A. Ivakhnenko · 2000 · 35 citations

, , +14

1–5 of 12

Authors

21

  1. FK
    Florent Krząkała

    Centre National de la Recherche Scientifique, France

    3 publications · 164 citations

    3

    h-index

  2. GB
    Giulio Biroli

    Centre National de la Recherche Scientifique, France

    3 publications · 80 citations

    3

    h-index

  3. BL
    Bruno Loureiro

    École Polytechnique Fédérale de Lausanne, Switzerland

    2 publications · 111 citations

    2

    h-index

  4. LS
    Levent Sagun

    New York University, United States

    2 publications · 27 citations

    2

    h-index

  5. LZ
    Lenka Zdeborová

    Centre National de la Recherche Scientifique, France

    2 publications · 111 citations

    2

    h-index

1–5 of 21

Institutions

16

  1. Google (United States)

    Mountain View, United States

    1 h-index

    2 publications

    70 citations

  2. Laboratoire de Physique de l'Ecole Normale Supérieure

    Paris, France

    1 h-index

    1 publications

    79 citations

  3. University of California, Berkeley

    Berkeley, United States

    1 h-index

    1 publications

    191 citations

  4. Meta (Israel)

    Tel Aviv, Israel

    1 h-index

    1 publications

    16 citations

  5. University of Genoa

    Genoa, Italy

    1 h-index

    3 publications

    66 citations

  6. Centre National de la Recherche Scientifique

    Paris, France

    1 h-index

    1 publications

    79 citations

  7. Chinese Academy of Meteorological Sciences

    Beijing, China

    1 h-index

    1 publications

    13 citations

  8. Institute of Psychology, Chinese Academy of Sciences

    Beijing, China

    1 h-index

    2 publications

    24 citations

1–8 of 16

Venues

  1. arXiv (Cornell University)

    Repository · 5 publications · 384 citations

    5

    h-index

  2. Journal of Statistical Mechanics Theory and Experiment

    JSTAT · 2 publications · 90 citations

    2

    h-index

  3. Neurocomputing

    1 publications · 22 citations

    1

    h-index

  4. Communications on Pure and Applied Mathematics

    1 publications · 191 citations

    1

    h-index

  5. Quarterly Journal of Experimental Psychology

    1 publications · 12 citations

    1

    h-index

1–5