mlsanityData to 7 Oct 2026

Solomonoff induction

arXiv 2603.20274 ↗First posted 17 Mar 2026cs.FL cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

This chapter discusses the Solomonoff approach to universal prediction. The crucial ingredient in the approach is the notion of computability, and I present the main idea as an attempt to meet two plausible computability desiderata for a universal predictor. This attempt is unsuccessful, which is shown by a generalization of a diagonalization argument due to Putnam. I then critically discuss purported gains of the approach, in particular it providing a foundation for the methodological principle of Occam's razor, and it serving as a theoretical ideal for the development of machine learning methods.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 15 of its 55 references that are in the map. First posted on arXiv 17 Mar 2026.

Builds on

15 of 55 references.

References · 15

  1. 2023Language Modeling Is Compressioncited by 225
  2. 2018Deep learning generalizes because the parameter-function map is biased towards simple functionscited by 180
  3. 2022Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functionscited by 68
  4. 2021The Modern Mathematics of Deep Learningcited by 63
  5. 2023The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learningcited by 63
  6. 2025Deep Learning is Not So Mysterious or Differentcited by 55
  7. 2024Learning Universal Predictorscited by 29
  8. 2023Deep neural networks have an inbuilt Occam's razorcited by 28
  9. 2022The no-free-lunch theorems of supervised learningcited by 16
  10. 2016Death and Suicide in Universal Artificial Intelligencecited by 9
  11. 2024Transformers As Approximations of Solomonoff Inductioncited by 6
  12. 2020Absolutely No Free Lunches!cited by 4
3 more
  1. 2022A Dilemma for Solomonoff Predictioncited by 4
  2. 2025Value Under Ignorance in Universal Artificial Intelligencecited by 3
  3. 2015On the Computability of Solomonoff Induction and Knowledge-Seekingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Benign interpolation and Occam's razorcited by 0
  2. 2026Understanding Generalization Requires Universal Inductioncited by 0