# A Dilemma for Solomonoff Prediction

arXiv: https://arxiv.org/abs/2206.06473 · HTML: https://mlsanity.com/paper/2206.06473/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 44 references that are in the map.
- First posted on arXiv 13 Jun 2022.

## Builds on (most cited first, 1 of 1)

- [On Accuracy and Coherence with Infinite Opinion Sets](https://mlsanity.com/paper/2007.14490/) (2020)

## Built on by (most cited first, 4 of 4)

- [Solomonoff induction](https://mlsanity.com/paper/2603.20274/) (2026)
- [Multiclass classification utilising an estimated algorithmic probability prior](https://mlsanity.com/paper/2212.07426/) (2022)
- [Simplicity bias, algorithmic probability, and the random logistic map](https://mlsanity.com/paper/2401.00593/) (2023)
- [Understanding Generalization Requires Universal Induction](https://mlsanity.com/paper/2609.34458/) (2026)

## Abstract (arXiv)

The framework of Solomonoff prediction assigns prior probability to hypotheses inversely proportional to their Kolmogorov complexity. There are two well-known problems. First, the Solomonoff prior is relative to a choice of Universal Turing machine. Second, the Solomonoff prior is not computable. However, there are responses to both problems. Different Solomonoff priors converge with more and more data. Further, there are computable approximations to the Solomonoff prior. I argue that there is a tension between these two responses. This is because computable approximations to Solomonoff prediction do not always converge.