Learnability can be undecidable

Shai Ben-David, Pavel Hrubeš, Shay Moran, Amir Shpilka, Amir Yehudayoff

Research output: Contribution to journalArticlepeer-review

Abstract

The mathematical foundations of machine learning play a key role in the development of the field. They improve our understanding and provide tools for designing new learning paradigms. The advantages of mathematics, however, sometimes come with a cost. Gödel and Cohen showed, in a nutshell, that not everything is provable. Here we show that machine learning shares this fate. We describe simple scenarios where learnability cannot be proved nor refuted using the standard axioms of mathematics. Our proof is based on the fact the continuum hypothesis cannot be proved nor refuted. We show that, in some cases, a solution to the ‘estimating the maximum’ problem is equivalent to the continuum hypothesis. The main idea is to prove an equivalence between learnability and compression.

Original languageEnglish
Pages (from-to)44-48
Number of pages5
JournalNature Machine Intelligence
Volume1
Issue number1
DOIs
StatePublished - 1 Jan 2019

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Learnability can be undecidable'. Together they form a unique fingerprint.

Cite this