# Solomonoff induction

arXiv: https://arxiv.org/abs/2603.20274 · HTML: https://mlsanity.com/paper/2603.20274/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 55 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 15 of 15)

- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [Deep learning generalizes because the parameter-function map is biased towards simple functions](https://mlsanity.com/paper/1805.08522/) (2018)
- [Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions](https://mlsanity.com/paper/2211.12316/) (2022)
- [The Modern Mathematics of Deep Learning](https://mlsanity.com/paper/2105.04026/) (2021)
- [The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning](https://mlsanity.com/paper/2304.05366/) (2023)
- [Deep Learning is Not So Mysterious or Different](https://mlsanity.com/paper/2503.02113/) (2025)
- [Learning Universal Predictors](https://mlsanity.com/paper/2401.14953/) (2024)
- [Deep neural networks have an inbuilt Occam's razor](https://mlsanity.com/paper/2304.06670/) (2023)
- [The no-free-lunch theorems of supervised learning](https://mlsanity.com/paper/2202.04513/) (2022)
- [Death and Suicide in Universal Artificial Intelligence](https://mlsanity.com/paper/1606.00652/) (2016)
- [Transformers As Approximations of Solomonoff Induction](https://mlsanity.com/paper/2408.12065/) (2024)
- [Absolutely No Free Lunches!](https://mlsanity.com/paper/2005.04791/) (2020)
- [A Dilemma for Solomonoff Prediction](https://mlsanity.com/paper/2206.06473/) (2022)
- [Value Under Ignorance in Universal Artificial Intelligence](https://mlsanity.com/paper/2512.17086/) (2025)
- [On the Computability of Solomonoff Induction and Knowledge-Seeking](https://mlsanity.com/paper/1507.04124/) (2015)

## Built on by (most cited first, 2 of 2)

- [Benign interpolation and Occam's razor](https://mlsanity.com/paper/2608.03386/) (2026)
- [Understanding Generalization Requires Universal Induction](https://mlsanity.com/paper/2609.34458/) (2026)

## 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.