In computational learning theory, probably approximately correct (PAC) learning is a framework for mathematical analysis of machine learning.
It was proposed in 1984 by Leslie Valiant.
[1] In this framework, the learner receives samples and must select a generalization function (called the hypothesis) from a certain class of possible functions.
The goal is that, with high probability (the "probably" part), the selected function will have low generalization error (the "approximately correct" part).
The learner must be able to learn the concept given any arbitrary approximation ratio, probability of success, or distribution of the samples.
The model was later extended to treat noise (misclassified samples).
An important innovation of the PAC framework is the introduction of computational complexity theory concepts to machine learning.
In particular, the learner is expected to find efficient functions (time and space requirements bounded to a polynomial of the example size), and the learner itself must implement an efficient procedure (requiring an example count bounded to a polynomial of the concept size, modified by the approximation and likelihood bounds).
In order to give the definition for something that is PAC-learnable, we first have to introduce some terminology.
The first is the problem of character recognition given an array of
bits encoding a binary-valued image.
The other example is the problem of finding an interval that will correctly classify points within the interval as positive and the points outside of the range as negative.
be a set called the instance space or the encoding of all the samples.
In the character recognition problem, the instance space is
In the interval problem the instance space,
, is the set of all bounded intervals in
denotes the set of all real numbers.
One concept is the set of all patterns of bits in
that encode a picture of the letter "P".
This could be the set of all subsets of the array of bits that are skeletonized 4-connected (width of the font is 1).
be a procedure that draws an example,
and gives the correct label
(and other relevant parameters of the class
that has an average error less than or equal to
is (efficiently) PAC learnable (or distribution-free PAC learnable).
is a PAC learning algorithm for