Concept

Contraction mapping

Summary

In mathematics, a contraction mapping, or contraction or contractor, on a metric space (M, d) is a function f from M to itself, with the property that there is some real number such that for all x and y in M, The smallest such value of k is called the Lipschitz constant of f. Contractive maps are sometimes called Lipschitzian maps. If the above condition is instead satisfied for k ≤ 1, then the mapping is said to be a non-expansive map. More generally, the idea of a contractive mapping can be defined for maps between metric spaces. Thus, if (M, d) and (N, d) are two metric spaces, then is a contractive mapping if there is a constant such that for all x and y in M. Every contraction mapping is Lipschitz continuous and hence uniformly continuous (for a Lipschitz continuous function, the constant k is no longer necessarily less than 1). A contraction mapping has at most one fixed point. Moreover, the Banach fixed-point theorem states that every contraction mapping on a non-empty complete metric space has a unique fixed point, and that for any x in M the iterated function sequence x, f (x), f (f (x)), f (f (f (x))), ... converges to the fixed point. This concept is very useful for iterated function systems where contraction mappings are often used. Banach's fixed-point theorem is also applied in proving the existence of solutions of ordinary differential equations, and is used in one proof of the inverse function theorem. Contraction mappings play an important role in dynamic programming problems. A non-expansive mapping with can be generalized to a firmly non-expansive mapping in a Hilbert space if the following holds for all x and y in : where This is a special case of averaged nonexpansive operators with . A firmly non-expansive mapping is always non-expansive, via the Cauchy–Schwarz inequality. The class of firmly non-expansive maps is closed under convex combinations, but not compositions. This class includes proximal mappings of proper, convex, lower-semicontinuous functions, hence it also includes orthogonal projections onto non-empty closed convex sets.

Official source

https://en.wikipedia.org/wiki/Contraction_mapping

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Contraction mapping

Stable Nonconvex-Nonconcave Training via Linear Interpolation

Recursive evaluation and iterative contraction of N-body equivariant features

Efficient Proximal Mapping of the 1-path-norm of Shallow Networks

Recursive evaluation and iterative contraction of N-body equivariant features

Efficient Proximal Mapping of the 1-path-norm of Shallow Networks

Stable Nonconvex-Nonconcave Training via Linear Interpolation