Abstract
In this chapter, we study the problems of concept and function learning in the case where the samples are drawn in accordance with a known fixed distribution. Various necessary and/or sufficient conditions are presented for a concept class or a function class to be learnable. The principal results of the chapter can be summarized as follows: Suppose the input sequence to the learning algorithm is i.i.d. Then we have the following:
-
1.
If a function class F (or a concept class C) has the property of uniform convergence of empirical means, then it is also ASEC learnable. However, the converse is not true in general — there exist function classes that are ASEC learnable even though they do not possess the UCEM property.
-
2.
A function class is PUAC learnable if it possesses a property known as the “shrinking width” property. The shrinking width property is also a necessary condition in order for every consistent algorithm to be PU AC.
-
3.
Similarly, there is a necessary and sufficient condition for a function family to be consistently PAC learnable.
-
4.
It can be shown that PUAC learnability is equivalent to consistent PUAC learnabilit. In contrast, PAC learnability is not equivalent in general to consistent PAC learnability.
-
5.
A function class (or a concept class) is learnable if it satisfies a property known as “finite metric entropy.”
-
6.
In order for a concept class to be learnable, the finite metric entropy condition is necessary as well as sufficient; however, for a function class to be learnable, the finite metric entropy condition is sufficient but is not necessary in general.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag London
About this chapter
Cite this chapter
Vidyasagar, M. (2003). Learning Under a Fixed Probability Measure. In: Learning and Generalisation. Communications and Control Engineering. Springer, London. https://doi.org/10.1007/978-1-4471-3748-1_6
Download citation
DOI: https://doi.org/10.1007/978-1-4471-3748-1_6
Publisher Name: Springer, London
Print ISBN: 978-1-84996-867-6
Online ISBN: 978-1-4471-3748-1
eBook Packages: Springer Book Archive