Results 1  10
of
67
Computability of probability measures and MartinLöf randomness over metric spaces
, 709
"... 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 that any computable metric space with a computable probability ..."
Abstract

Cited by 38 (11 self)
 Add to MetaCart
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 that any computable metric space with a computable probability measure is isomorphic to the Cantor space in a computable and measuretheoretic sense. We show that any computable metric space admits a universal uniform randomness test (without further assumption). Key words: Computability, computable metric spaces, computable measures, Kolmogorov complexity, algorithmic randomness, randomness tests. 1
An Application of MartinLöf Randomness to Effective Probability Theory
 COMPUTABILITY IN EUROPE (CIE 2009), HEIDELBERG: GERMANY
, 2009
"... In this paper we provide a framework for computable analysis of measure, probability and integration theories. We work on computable metric spaces with computable Borel probability measures. We introduce and study the framework of layerwise computability which lies on MartinLöf randomness and the ..."
Abstract

Cited by 24 (7 self)
 Add to MetaCart
In this paper we provide a framework for computable analysis of measure, probability and integration theories. We work on computable metric spaces with computable Borel probability measures. We introduce and study the framework of layerwise computability which lies on MartinLöf randomness and the existence of a universal randomness test. We then prove characterizations of effective notions of measurability and integrability in terms of layerwise computability. On the one hand it gives a simple way of handling effective measure theory, on the other hand it provides powerful tools to study MartinLöf randomness, as illustrated in a sequel paper.
RANDOMNESS ON COMPUTABLE PROBABILITY SPACES  A DYNAMICAL POINT OF VIEW
, 2009
"... We extend the notion of randomness (in the version introduced by Schnorr) to computable Probability Spaces and compare it to a dynamical notion of randomness: typicality. Roughly, a point is typical for some dynamic, if it follows the statistical behavior of the system (Birkhoff’s pointwise ergodic ..."
Abstract

Cited by 18 (3 self)
 Add to MetaCart
We extend the notion of randomness (in the version introduced by Schnorr) to computable Probability Spaces and compare it to a dynamical notion of randomness: typicality. Roughly, a point is typical for some dynamic, if it follows the statistical behavior of the system (Birkhoff’s pointwise ergodic theorem). We prove that a point is Schnorr random if and only if it is typical for every mixing computable dynamics. To prove the result we develop some tools for the theory of computable probability spaces (for example, morphisms) that are expected to have other applications.
Measures and their random reals
 IN PREPARATION
"... We study the randomness properties of reals with respect to arbitrary probability measures on Cantor space. We show that every nonrecursive real is nontrivially random with respect to some measure. The probability measures constructed in the proof may have atoms. If one rules out the existence of ..."
Abstract

Cited by 14 (2 self)
 Add to MetaCart
We study the randomness properties of reals with respect to arbitrary probability measures on Cantor space. We show that every nonrecursive real is nontrivially random with respect to some measure. The probability measures constructed in the proof may have atoms. If one rules out the existence of atoms, i.e. considers only continuous measures, it turns out that every nonhyperarithmetical real is random for a continuous measure. On the other hand, examples of reals not random for a continuous measure can be found throughout the hyperarithmetical Turing degrees.
Effectively closed sets of measures and randomness
 Ann. Pure Appl. Logic
"... We show that if a real x ∈ 2ω is strongly Hausdorff Hhrandom, where h is a dimension function corresponding to a convex order, then it is also random for a continuous probability measure µ such that the µmeasure of the basic open cylinders shrinks according to h. The proof uses a new method to con ..."
Abstract

Cited by 12 (2 self)
 Add to MetaCart
(Show Context)
We show that if a real x ∈ 2ω is strongly Hausdorff Hhrandom, where h is a dimension function corresponding to a convex order, then it is also random for a continuous probability measure µ such that the µmeasure of the basic open cylinders shrinks according to h. The proof uses a new method to construct measures, based on effective (partial) continuous transformations and a basis theorem for Π0 1classes applied to closed sets of probability measures. We use the main result to give a new proof of Frostman’s Lemma, to derive a collapse of randomness notions for Hausdorff measures, and to provide a characterization of effective Hausdorff dimension similar to Frostman’s Theorem. 1
Algorithmic tests and randomness with respect to a class of measures
, 2011
"... This paper offers some new results on randomness with respect to classes of measures, along with a didactical exposition of their context based on results that appeared elsewhere. We start with the reformulation of the MartinLöf definition of randomness (with respect to computable measures) in term ..."
Abstract

Cited by 12 (3 self)
 Add to MetaCart
(Show Context)
This paper offers some new results on randomness with respect to classes of measures, along with a didactical exposition of their context based on results that appeared elsewhere. We start with the reformulation of the MartinLöf definition of randomness (with respect to computable measures) in terms of randomness deficiency functions. A formula that expresses the randomness deficiency in terms of prefix complexity is given (in two forms). Some approaches that go in another direction (from deficiency to complexity) are considered. The notion of Bernoulli randomness (independent coin tosses for an asymmetric coin with some probability p of head) is defined. It is shown that a sequence is Bernoulli if it is random with respect to some Bernoulli
A Constructive Version of Birkhoff’s Ergodic Theorem for MartinLöf Random Points
 INFORMATION AND COMPUTATION
, 2011
"... ..."
Hedging predictions in machine learning
 Comput. J
, 2007
"... Recent advances in machine learning make it possible to design efficient prediction algorithms for data sets with huge numbers of parameters. This article describes a new technique for ‘hedging ’ the predictions output by many such algorithms, including support vector machines, kernel ridge regressi ..."
Abstract

Cited by 12 (3 self)
 Add to MetaCart
(Show Context)
Recent advances in machine learning make it possible to design efficient prediction algorithms for data sets with huge numbers of parameters. This article describes a new technique for ‘hedging ’ the predictions output by many such algorithms, including support vector machines, kernel ridge regression, kernel nearest neighbours, and by many other stateoftheart methods. The hedged predictions for the labels of new objects include quantitative measures of their own accuracy and reliability. These measures are provably valid under the assumption of randomness, traditional in machine learning: the objects and their labels are assumed to be generated independently from the same probability distribution. In particular, it becomes possible to control (up to statistical fluctuations) the number of erroneous predictions by selecting a suitable confidence level. Validity being achieved automatically, the remaining goal of hedged prediction is efficiency: taking full account of the new objects ’ features and other available information to produce as accurate predictions as possible. This can be done successfully using the powerful machinery of modern machine learning. 1
Computability of probability measures and MartinLöf randomness over metric spaces
 Information and Computation
"... 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 that any computable metric space with a computable probability ..."
Abstract

Cited by 11 (5 self)
 Add to MetaCart
(Show Context)
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 that any computable metric space with a computable probability measure is isomorphic to the Cantor space in a computable and measuretheoretic sense. We show that any computable metric space admits a universal uniform randomness test (without further assumption). 1