Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Hoeffding decomposition of black-box models with dependent inputs

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • معلومة اضافية
    • Contributors:
      Performance, Risque Industriel, Surveillance pour la Maintenance et l’Exploitation (EDF R&D PRISME); EDF R&D (EDF R&D); EDF (EDF)-EDF (EDF); Institut de Mathématiques de Toulouse UMR5219 (IMT); Université Toulouse Capitole (UT Capitole); Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse); Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J); Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3); Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS); Saclay Industrial Lab for Artificial Intelligence Research (SINCLAIR AI Lab); THALES France -TOTAL FINA ELF-EDF (EDF); Laboratoire de Probabilités, Statistique et Modélisation (LPSM (UMR_8001)); Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité); GDR2172 - Quantification d'incertitudes (RT-UQ) (RT-UQ); Institut National des Sciences Mathématiques et de leurs Interactions - CNRS Mathématiques (INSMI-CNRS)-Centre National de la Recherche Scientifique (CNRS)
    • بيانات النشر:
      HAL CCSD
    • الموضوع:
      2024
    • Collection:
      Université Toulouse 2 - Jean Jaurès: HAL
    • نبذة مختصرة :
      One of the main challenges for interpreting black-box models is the ability to uniquely decompose square-integrable functions of non-independent random inputs into a sum of functions of every possible subset of variables. However, dealing with dependencies among inputs can be complicated. We propose a novel framework to study this problem, linking three domains of mathematics: probability theory, functional analysis, and combinatorics. We show that, under two reasonable assumptions on the inputs (non-perfect functional dependence and non-degenerate stochastic dependence), it is always possible to decompose such a function uniquely. This generalizes the well-known Hoeffding decomposition. The elements of this decomposition can be expressed using oblique projections and allow for novel interpretability indices for evaluation and variance decomposition purposes. The properties of these novel indices are studied and discussed. This generalization offers a path towards a more precise uncertainty quantification, which can benefit sensitivity analysis and interpretability studies whenever the inputs are dependent. This decomposition is illustrated analytically, and the challenges for adopting these results in practice are discussed.
    • Relation:
      info:eu-repo/semantics/altIdentifier/arxiv/2310.06567; hal-04233915; https://hal.science/hal-04233915; https://hal.science/hal-04233915v2/document; https://hal.science/hal-04233915v2/file/GenAnova-preprint.pdf; ARXIV: 2310.06567
    • Rights:
      info:eu-repo/semantics/OpenAccess
    • الرقم المعرف:
      edsbas.C825BC2A