An equivalence between learning of data and probability distributions, and some applications

01/05/2018
by   George Barmpalias, et al.
0

Algorithmic learning theory traditionally studies the learnability of effective infinite binary sequences (reals), while recent work by (Vitanyi and Chater 2017) and (Bienvenu et al. 2014) has adapted this framework to the study of learnability of effective probability distributions from random data. We prove that for certain families of probability measures that are parametrized by reals, learnability of a subclass of probability measures is equivalent to learnability of the class of the corresponding real parameters. This equivalence allows to transfer results from classical algorithmic theory to learning theory of probability measures. We present a number of such applications, providing new results regarding EX and BC learnability of classes of measures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/05/2018

Equivalences between learning of data and probability distributions, and their applications

Algorithmic learning theory traditionally studies the learnability of ef...
research
10/31/2017

Algorithmic learning of probability distributions from random data in the limit

We study the problem of identifying a probability distribution for some ...
research
11/04/2021

Effective weak and vague convergence of measures on the real line

We expand our effective framework for weak convergence of measures on th...
research
06/08/2021

Markov Chains Generated by Convolutions of Orthogonality Measures

About two dozens of exactly solvable Markov chains on one-dimensional fi...
research
09/21/2019

Using theoretical ROC curves for analysing machine learning binary classifiers

Most binary classifiers work by processing the input to produce a scalar...
research
03/27/2013

Foundations of Probability Theory for AI - The Application of Algorithmic Probability to Problems in Artificial Intelligence

This paper covers two topics: first an introduction to Algorithmic Compl...
research
03/13/2023

On the Algorithmic Information Between Probabilities

We extend algorithmic conservation inequalities to probability measures....

Please sign up or login with your details

Forgot password? Click here to reset