Occam’s razor is the principle stating that, all else being equal, simpler explanations for a set of observations are to be preferred to more complex ones. This idea can be made precise in the context of statistical inference, where the same quantitative notion of complexity of a statistical model emerges naturally from different approaches based on Bayesian model selection and information theory. The broad applicability of this mathematical formulation suggests a normative model of decision-making under uncertainty: complex explanations should be penalized according to this common measure of complexity. However, little is known about if and how humans intuitively quantify the relative complexity of competing interpretations of noisy data. Here we measure the sensitivity of naive human subjects to statistical model complexity. Our data show that human subjects bias their decisions in favor of simple explanations based not only on the dimensionality of the alternatives (number of model parameters), but also on finer-grained aspects of their geometry. In particular, as predicted by the theory, models intuitively judged as more complex are not only those with more parameters, but also those with larger volume and prominent curvature or boundaries. Our results imply that principled notions of statistical model complexity have direct quantitative relevance to human decision-making.

Effect of Geometric Complexity on Intuitive Model Selection / Piasini, E.; Balasubramanian, V.; Gold, J. I.. - 13163:(2022), pp. 1-24. (Intervento presentato al convegno 7th International Conference on Machine Learning, Optimization, and Data Science, LOD 2021 tenutosi a Lod nel 2021) [10.1007/978-3-030-95467-3_1].

Effect of Geometric Complexity on Intuitive Model Selection

Piasini, E.
;
Balasubramanian, V.;
2022-01-01

Abstract

Occam’s razor is the principle stating that, all else being equal, simpler explanations for a set of observations are to be preferred to more complex ones. This idea can be made precise in the context of statistical inference, where the same quantitative notion of complexity of a statistical model emerges naturally from different approaches based on Bayesian model selection and information theory. The broad applicability of this mathematical formulation suggests a normative model of decision-making under uncertainty: complex explanations should be penalized according to this common measure of complexity. However, little is known about if and how humans intuitively quantify the relative complexity of competing interpretations of noisy data. Here we measure the sensitivity of naive human subjects to statistical model complexity. Our data show that human subjects bias their decisions in favor of simple explanations based not only on the dimensionality of the alternatives (number of model parameters), but also on finer-grained aspects of their geometry. In particular, as predicted by the theory, models intuitively judged as more complex are not only those with more parameters, but also those with larger volume and prominent curvature or boundaries. Our results imply that principled notions of statistical model complexity have direct quantitative relevance to human decision-making.
2022
Machine Learning, Optimization, and Data Science
13163
1
24
978-3-030-95466-6
978-3-030-95467-3
Springer Science and Business Media Deutschland GmbH
Piasini, E.; Balasubramanian, V.; Gold, J. I.
File in questo prodotto:
File Dimensione Formato  
geometric_complexity_model_selection.pdf

Open Access dal 03/02/2023

Descrizione: Author post-print version.
Tipologia: Documento in Post-print
Licenza: Non specificato
Dimensione 2.16 MB
Formato Adobe PDF
2.16 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11767/127531
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact