English
Related papers

Related papers: On Semimeasures Predicting Martin-Loef Random Sequ…

200 papers

Solomonoff's inductive learning model is a powerful, universal and highly elegant theory of sequence prediction. Its critical flaw is that it is incomputable and thus cannot be used in practice. It is sometimes suggested that it may still…

Artificial Intelligence · Computer Science 2007-05-23 Shane Legg

In this paper we investigate algorithmic randomness on more general spaces than the Cantor space, namely computable metric spaces. To do this, we first develop a unified framework allowing computations with probability measures. We show…

Information Theory · Computer Science 2008-07-23 Mathieu Hoyrup , Cristobal Rojas

The Bayesian framework is a well-studied and successful framework for inductive reasoning, which includes hypothesis testing and confirmation, parameter estimation, sequence prediction, classification, and regression. But standard…

Statistics Theory · Mathematics 2008-06-26 Marcus Hutter

This paper explores a novel definition of Schnorr randomness for noncomputable measures. We say $x$ is uniformly Schnorr $\mu$-random if $t(\mu,x)<\infty$ for all lower semicomputable functions $t(\mu,x)$ such that $\mu\mapsto\int…

Logic · Mathematics 2017-08-08 Jason Rute

Solomonoff sequence prediction is a scheme to predict digits of binary strings without knowing the underlying probability distribution. We call a prediction scheme informed when it knows the true probability distribution of the sequence.…

Artificial Intelligence · Computer Science 2007-05-23 Marcus Hutter

Suppose that we have a method which estimates the conditional probabilities of some unknown stochastic source and we use it to guess which of the outcomes will happen. We want to make a correct guess as often as it is possible. What…

Probability · Mathematics 2023-02-10 Łukasz Dębowski , Tomasz Steifer

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…

Formal Languages and Automata Theory · Computer Science 2026-03-24 Tom F. Sterkenburg

Let $M$ be a complete Riemannian manifold, $N\in \NN$ and $p\ge 1$. We prove that almost everywhere on $x=(x_1,...,x_N)\in M^N$ for Lebesgue measure in $M^N$, the measure $\di \mu(x)=\f1N\sum_{k=1}^N\d_{x_k}$ has a unique $p$-mean $e_p(x)$.…

Probability · Mathematics 2012-07-16 Marc Arnaudon , Laurent Miclo

In this paper, we study Bernoulli random sequences, i.e., sequences that are Martin-L\"of random with respect to a Bernoulli measure $\mu_p$ for some $p\in[0,1]$, where we allow for the possibility that $p$ is noncomputable. We focus in…

Logic · Mathematics 2019-03-26 Christopher P. Porter

In the theory of algorithmic randomness, several notions of random sequence are defined via a game-theoretic approach, and the notions that received most attention are perhaps Martin-Loef randomness and computable randomness. The latter…

Computational Complexity · Computer Science 2009-07-15 Laurent Bienvenu , Rupert Hoelzl , Thorsten Kraling , Wolfgang Merkle

Given a compact metric space (X,d) equipped with a non-atomic, probability measure m and a real, positive decreasing function p we consider a `natural' class of limsup subsets La(p) of X. The classical limsup sets of `well approximable'…

Number Theory · Mathematics 2007-05-23 Victor Beresnevich , Detta Dickinson , Sanju Velani

The paper considers quantitative versions of different randomness notions: algorithmic test measures the amount of non-randomness (and is infinite for non-random sequences). We start with computable measures on Cantor space (and Martin-Lof…

Logic · Mathematics 2011-05-27 Laurent Bienvenu , Peter Gacs , Mathieu Hoyrup , Cristobal Rojas , Alexander Shen

We study Martin-L\"{o}f random (ML-random) points on computable probability measures on sample and parameter spaces (Bayes models). We consider variants of conditional randomness defined by ML-randomness on Bayes models and those of…

Information Theory · Computer Science 2023-04-24 Hayato Takahashi

We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor $M$ from the true distribution $mu$ by the algorithmic complexity of $mu$. Here…

Machine Learning · Computer Science 2007-07-16 A. Chernov , M. Hutter , J. Schmidhuber

The remarkable results of Foster and Vohra was a starting point for a series of papers which show that any sequence of outcomes can be learned (with no prior knowledge) using some universal randomized forecasting algorithm and…

Artificial Intelligence · Computer Science 2008-06-27 Vladimir V. V'yugin

Standard practice in Hidden Markov Model (HMM) selection favors the candidate with the highest full-sequence likelihood, although this is equivalent to making a decision based on a single realization. We introduce a \emph{fragment-based}…

Methodology · Statistics 2025-05-01 Carlos M. Hernandez-Suarez , Osval A. Montesinos-López

Ray Solomonoff invented the notion of universal induction featuring an aptly termed "universal" prior probability function over all possible computable environments. The essential property of this prior was its ability to dominate all other…

Information Theory · Computer Science 2011-11-17 Ian Wood , Peter Sunehag , Marcus Hutter

It is shown that operator-selfdecomposable measures, or more precisely their Urbanik decomposability semigroups, induce generalized Mehler semigroups of bounded linear operators. Moreover, those semigroups can be represented as random…

Probability · Mathematics 2010-09-15 Zbigniew J. Jurek

The problem is that of sequential probability forecasting for finite-valued time series. The data is generated by an unknown probability distribution over the space of all one-way infinite sequences. It is known that this measure belongs to…

Statistics Theory · Mathematics 2016-11-02 Daniil Ryabko

Shape constraints yield flexible middle grounds between fully nonparametric and fully parametric approaches to modeling distributions of data. The specific assumption of log-concavity is motivated by applications across economics, survival…

Methodology · Statistics 2024-04-16 Robin Dunn , Aditya Gangrade , Larry Wasserman , Aaditya Ramdas