English
Related papers

Related papers: Universal probability-free prediction

200 papers

Conformal predictors provide set or functional predictions that are valid under the assumption of randomness, i.e., under the assumption of independent and identically distributed data. The question asked in this paper is whether there are…

Machine Learning · Computer Science 2025-06-10 Vladimir Vovk

Algorithmic information theory studies description complexity and randomness and is now a well known field of theoretical computer science and mathematical logic. There are several textbooks and monographs devoted to this theory where one…

Information Theory · Computer Science 2015-04-21 Alexander Shen

Kolmogorov complexity and algorithmic probability are defined only up to an additive resp. multiplicative constant, since their actual values depend on the choice of the universal reference computer. In this paper, we analyze a natural…

Information Theory · Computer Science 2010-03-29 Markus Mueller

To what extent can we forecast a time series without fitting to historical data? Can universal patterns of probability help in this task? Deep relations between pattern Kolmogorov complexity and pattern probability have recently been used…

Data Analysis, Statistics and Probability · Physics 2023-01-25 Kamaludin Dingle , Rafiq Kamal , Boumediene Hamzi

This paper argues for a wider use of the functional theory of randomness, a modification of the algorithmic theory of randomness getting rid of unspecified additive constants. Both theories are useful for understanding relationships between…

Machine Learning · Computer Science 2025-06-10 Vladimir Vovk

The use of algorithmic information theory (Kolmogorov complexity theory) to explain the relation between mathematical probability theory and `real world' is discussed.

History and Overview · Mathematics 2015-05-13 Alexander Shen

We propose a measure based upon the fundamental theoretical concept in algorithmic information theory that provides a natural approach to the problem of evaluating $n$-dimensional complexity by using an $n$-dimensional deterministic Turing…

Computational Complexity · Computer Science 2015-08-27 Hector Zenil , Fernando Soler-Toscano , Jean-Paul Delahaye , Nicolas Gauvrit

We construct the universal type structure for conditional probability systems without any topological assumption, namely a type structure that is terminal, belief-complete, and non-redundant. In particular, in order to obtain the…

Logic in Computer Science · Computer Science 2017-08-02 Pierfrancesco Guarino

The probability distribution P from which the history of our universe is sampled represents a theory of everything or TOE. We assume P is formally describable. Since most (uncountably many) distributions are not, this imposes a strong…

Quantum Physics · Physics 2007-05-23 Juergen Schmidhuber

The Coding Theorem of L.A. Levin connects unconditional prefix Kolmogorov complexity with the discrete universal distribution. There are conditional versions referred to in several publications but as yet there exist no written proofs in…

Information Theory · Computer Science 2013-01-23 Paul M. B. Vitanyi

We show that Kolmogorov complexity and such its estimators as universal codes (or data compression methods) can be applied for hypotheses testing in a framework of classical mathematical statistics. The methods for identity testing and…

Computational Complexity · Computer Science 2007-05-23 Boris Ryabko , Jaakko Astola , Alex Gammerman

For a broad class of input-output maps, arguments based on the coding theorem from algorithmic information theory (AIT) predict that simple (low Kolmogorov complexity) outputs are exponentially more likely to occur upon uniform random…

Data Analysis, Statistics and Probability · Physics 2019-10-03 Kamaludin Dingle , Guillermo Valle Pérez , Ard A. Louis

While Kolmogorov complexity is the accepted absolute measure of information content of an individual finite object, a similarly absolute notion is needed for the relation between an individual data sample and an individual model summarizing…

Statistics Theory · Mathematics 2007-07-16 Peter Gacs , John Tromp , Paul Vitanyi

We introduce Conformal Decision Theory, a framework for producing safe autonomous decisions despite imperfect machine learning predictions. Examples of such decisions are ubiquitous, from robot planning algorithms that rely on pedestrian…

First the crucial but very confidential fact is brought into evidence that, as Kolmogorov himself repeatedly claimed, there exists no abstract theory of probabilities, simply because the factual concept of probability is itself unachieved:…

Quantum Physics · Physics 2008-01-18 Mioara Mugur-Schachter

A selection of the relevant theorems of Probability Theory that comes directly from Kolmogorov's axioms, Set Theory basic results, definitions and rules of inference are listed and proven in a systematic approach, aiming the student who…

General Mathematics · Mathematics 2022-06-14 Diego J. Raposo

We introduce algorithmic information theory, also known as the theory of Kolmogorov complexity. We explain the main concepts of this quantitative approach to defining `information'. We discuss the extent to which Kolmogorov's and Shannon's…

Information Theory · Computer Science 2008-09-17 Peter D. Grunwald , Paul M. B. Vitanyi

We consider the problem of inferring the probability distribution associated with a language, given data consisting of an infinite sequence of elements of the languge. We do this under two assumptions on the algorithms concerned: (i) like a…

Machine Learning · Computer Science 2014-07-16 Paul M. B. Vitanyi , Nick Chater

TThe problem is to identify a probability associated with a set of natural numbers, given an infinite data sequence of elements from the set. If the given sequence is drawn i.i.d. and the probability mass function involved (the target)…

Machine Learning · Computer Science 2014-07-14 Paul M. B. Vitanyi , Nick Chater

Conformal prediction is a general distribution-free approach for constructing prediction sets combined with any machine learning algorithm that achieve valid marginal or conditional coverage in finite samples. Ordinal classification is…

Methodology · Statistics 2024-11-05 Subhrasish Chakraborty , Chhavi Tyagi , Haiyan Qiao , Wenge Guo
‹ Prev 1 2 3 10 Next ›