Pessimistic Meta-Induction and Its Limits: Lessons from Frequentist Statistics and Machine Learning Theory

arXiv:2608.17213v1 Announce Type: new Abstract: This paper challenges the pessimistic meta-inductive argument against scientific realism by undermining its inductive step rather than its historical premise. Although related challenges already exist, I develop a new one. Drawing on a general epistemology of scientific inference developed in frequentist statistics, machine learning, and formal epistemology, I evaluate induction in terms of convergence to the truth. I argue that ordinary enumerative induction can achieve everywhere convergence, whereas meta-induction fails even to achieve almost everywhere convergence. Indeed, in the problem context where meta-induction arises, the failure is deeper: no inference method whatsoever achieves almost everywhere convergence.

Related

• A short tour of operator learning theory: Convergence rates, statistical limits, and open questions
• There Will Be a Scientific Theory of Deep Learning
• Hierarchical Solomonoff Induction: An Unbounded Machine Learning Model

Source: arXiv cs.LG | 2026-08-19