Results 71 to 80 of about 2,110,154 (170)

Minimum Description Length Codes Are Critical

Entropy, 2018
In the Minimum Description Length (MDL) principle, learning from the data is equivalent to an optimal coding problem. We show that the codes that achieve optimal compression in MDL are critical in a very precise sense.
Ryan John Cubero, Matteo Marsili, Yasser Roudi   +2 more
doaj   +1 more source

Large Deviations for Mixtures

Electronic Communications in Probability, 2004
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +2 more sources

Guessing Revisited: A Large Deviations Approach

, 2010
The problem of guessing a random string is revisited. A close relation between guessing and compression is first established. Then it is shown that if the sequence of distributions of the information spectrum satisfies the large deviation property with a
Hanawal, Manjesh Kumar, Sundaresan, Rajesh   +1 more
core  

Precise Large Deviations for Subexponential Distributions in a Multi Risk Model

Risks, 2018
The precise large deviations asymptotics for the sums of independent identical random variables when the distribution of the summand belongs to the class S ∗ of heavy tailed distributions is studied.
Dimitrios G. Konstantinides
doaj   +1 more source

High-dimensional random landscapes: From typical to large deviations

SciPost Physics Lecture Notes
We discuss tools and concepts that emerge when studying high-dimensional random landscapes, i.e., random functions on high-dimensional spaces. As an illustrative example, we consider an inference problem in two forms: low-rank matrix estimation (case 1 ...
Valentina Ros
doaj   +1 more source

Probability Distributions with Singularities

Entropy, 2019
In this paper we review some general properties of probability distributions which exhibit a singular behavior. After introducing the matter with several examples based on various models of statistical mechanics, we discuss, with the help of such ...
Federico Corberi, Alessandro Sarracino
doaj   +1 more source

Nonlinear large deviations

Advances in Mathematics, 2016
We present a general technique for computing large deviations of nonlinear functions of independent Bernoulli random variables. The method is applied to compute the large deviation rate functions for subgraph counts in sparse random graphs. Previous technology, based on Szemeredi's regularity lemma, works only for dense graphs.
Chatterjee, Sourav, Dembo, Amir
openaire   +2 more sources

Chaotic Hypothesis and Universal Large Deviations Properties

, 1998
Chaotic systems arise naturally in Statistical Mechanics and in Fluid Dynamics. A paradigm for their modelization are smooth hyperbolic systems. Are there consequences that can be drawn simply by assuming that a system is hyperbolic?
Gallavotti, Giovanni
core  

Large deviations for Branching Processes in Random Environment

, 2008
A branching process in random environment $(Z_n, n \in \N)$ is a generalization of Galton Watson processes where at each generation the reproduction law is picked randomly.
Bansaye, Vincent, Berestycki, Julien
core  

Large deviations

, 2020
[en] The objective of this project is to give an introduction to the theory of large deviations (LDP), a topic in stochastic analysis that can be described as the asymptotic evaluation of small probabilities at exponential scale. We start with the fundamental and initial result by Cramér (1938) and then, we formulate general LDP principles.
openaire   +1 more source