par Bontempi, Gianluca
Référence Lecture notes in computer science, 11943 LNCS, page (232-243)
Publication Publié, 2019-06-01
Article révisé par les pairs
Résumé : The problem of induction is a central problem in philosophy of science and concerns whether it is sound or not to extract laws from observational data. Nowadays, this issue is more relevant than ever given the pervasive and growing role of the data discovery process in all sciences. If on one hand induction is routinely employed by automatic machine learning techniques, on the other most of the philosophical work criticises induction as if an alternative could exist. But is there indeed a reliable alternative to induction? Is it possible to discover or predict something in a non inductive manner? This paper formalises the question on the basis of statistical notions (bias, variance, mean squared error) borrowed from estimation theory and statistical machine learning. The result is a justification of induction as rational behaviour. In a decision-making process a behaviour is rational if it is based on making choices that result in the most optimal level of benefit or utility. If we measure utility in a prediction context in terms of expected accuracy, it follows that induction is the rational way of conduct.