Algorithmic randomness and the weak merging of computable probability measures
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914376870526976 |
|---|---|
| author | Huttegger, Simon M. Walsh, Sean Blando, Francesca Zaffora |
| author_facet | Huttegger, Simon M. Walsh, Sean Blando, Francesca Zaffora |
| contents | We characterize Martin-Löf randomness and Schnorr randomness in terms of the merging of opinions, along the lines of the Blackwell-Dubins Theorem. After setting up a general framework for defining notions of merging randomness, we focus on finite horizon events, that is, on weak merging in the sense of Kalai-Lehrer. In contrast to Blackwell-Dubins and Kalai-Lehrer, we consider not only the total variational distance but also the Hellinger distance and the Kullback-Leibler divergence. Our main result is a characterization of Martin-Löf randomness and Schnorr randomness in terms of weak merging and the summable Kullback-Leibler divergence. The main proof idea is that the Kullback-Leibler divergence between $μ$ and $ν$, at a given stage of the learning process, is exactly the incremental growth, at that stage, of the predictable process of the Doob decomposition of the $ν$-submartingale $L(σ)=-\ln \frac{μ(σ)}{ν(σ)}$. These characterizations of algorithmic randomness notions in terms of the Kullback-Leibler divergence can be viewed as global analogues of Vovk's theorem on what transpires locally with individual Martin-Löf $μ$- and $ν$-random points and the Hellinger distance between $μ,ν$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00440 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Algorithmic randomness and the weak merging of computable probability measures Huttegger, Simon M. Walsh, Sean Blando, Francesca Zaffora Logic Information Theory Primary 03D32 Secondary: 60A10, 94A17 We characterize Martin-Löf randomness and Schnorr randomness in terms of the merging of opinions, along the lines of the Blackwell-Dubins Theorem. After setting up a general framework for defining notions of merging randomness, we focus on finite horizon events, that is, on weak merging in the sense of Kalai-Lehrer. In contrast to Blackwell-Dubins and Kalai-Lehrer, we consider not only the total variational distance but also the Hellinger distance and the Kullback-Leibler divergence. Our main result is a characterization of Martin-Löf randomness and Schnorr randomness in terms of weak merging and the summable Kullback-Leibler divergence. The main proof idea is that the Kullback-Leibler divergence between $μ$ and $ν$, at a given stage of the learning process, is exactly the incremental growth, at that stage, of the predictable process of the Doob decomposition of the $ν$-submartingale $L(σ)=-\ln \frac{μ(σ)}{ν(σ)}$. These characterizations of algorithmic randomness notions in terms of the Kullback-Leibler divergence can be viewed as global analogues of Vovk's theorem on what transpires locally with individual Martin-Löf $μ$- and $ν$-random points and the Hellinger distance between $μ,ν$. |
| title | Algorithmic randomness and the weak merging of computable probability measures |
| topic | Logic Information Theory Primary 03D32 Secondary: 60A10, 94A17 |
| url | https://arxiv.org/abs/2504.00440 |