English

Falsifiable implies Learnable

Machine Learning 2014-08-29 v1 Statistics Theory Machine Learning Statistics Theory

Abstract

The paper demonstrates that falsifiability is fundamental to learning. We prove the following theorem for statistical learning and sequential prediction: If a theory is falsifiable then it is learnable -- i.e. admits a strategy that predicts optimally. An analogous result is shown for universal induction.

Keywords

Cite

@article{arxiv.1408.6618,
  title  = {Falsifiable implies Learnable},
  author = {David Balduzzi},
  journal= {arXiv preprint arXiv:1408.6618},
  year   = {2014}
}
R2 v1 2026-06-22T05:42:24.049Z