Divergence (statistics)

In statistics and information geometry, divergence or a contrast function is a function which establishes the "distance" of one probability distribution to the other on a statistical manifold. The divergence is a weaker notion than that of the distance, in particular the divergence need not be symmetric (that is, in general the divergence from p to q is not equal to the divergence from q to p), and need not satisfy the triangle inequality.

Definition

Suppose S is a space of all probability distributions with common support. Then a divergence on S is a function D(· || ·): S×S → R satisfying ^[1]

1. D(p || q) ≥ 0 for all p, q ∈ S,
2. D(p || q) = 0 if and only if p = q,

The dual divergence D* is defined as

$D^{*}(p\parallel q)=D(q\parallel p).$

Geometrical properties

Many properties of divergences can be derived if we restrict S to be a statistical manifold, meaning that it can be parametrized with a finite-dimensional coordinate system θ, so that for a distribution p ∈ S we can write p = p(θ).

For a pair of points p, q ∈ S with coordinates θ_p and θ_q, denote the partial derivatives of D(p || q) as

${\begin{aligned}D((\partial _{i})_{p}\parallel q)\ \ &{\stackrel {{\mathrm {def}}}{=}}\ \ {\tfrac {\partial }{\partial \theta _{p}^{i}}}D(p\parallel q),\\D((\partial _{i}\partial _{j})_{p}\parallel (\partial _{k})_{q})\ \ &{\stackrel {{\mathrm {def}}}{=}}\ \ {\tfrac {\partial }{\partial \theta _{p}^{i}}}{\tfrac {\partial }{\partial \theta _{p}^{j}}}{\tfrac {\partial }{\partial \theta _{q}^{k}}}D(p\parallel q),\ \ {\mathrm {etc.}}\end{aligned}}$

Now we restrict these functions to a diagonal p = q, and denote ^[2]

${\begin{aligned}D[\partial _{i}\parallel \cdot ]\ &:\ p\mapsto D((\partial _{i})_{p}\parallel p),\\D[\partial _{i}\parallel \partial _{j}]\ &:\ p\mapsto D((\partial _{i})_{p}\parallel (\partial _{j})_{p}),\ \ {\mathrm {etc.}}\end{aligned}}$

By definition, the function D(p || q) is minimized at p = q, and therefore

${\begin{aligned}&D[\partial _{i}\parallel \cdot ]=D[\cdot \parallel \partial _{i}]=0,\\&D[\partial _{i}\partial _{j}\parallel \cdot ]=D[\cdot \parallel \partial _{i}\partial _{j}]=-D[\partial _{i}\parallel \partial _{j}]\ \equiv \ g_{{ij}}^{{(D)}},\end{aligned}}$

where matrix g^(D) is positive semi-definite and defines a unique Riemannian metric on the manifold S.

Divergence D(· || ·) also defines a unique torsion-free affine connection ∇^(D) with coefficients

$\Gamma _{{ij,k}}^{{(D)}}=-D[\partial _{i}\partial _{j}\parallel \partial _{k}],$

and the dual to this connection ∇* is generated by the dual divergence D*.

Thus, a divergence D(· || ·) generates on a statistical manifold a unique dualistic structure (g^(D), ∇^(D), ∇^(D*)). The converse is also true: every torsion-free dualistic structure on a statistical manifold is induced from some globally defined divergence function (which however need not be unique).^[3]

For example, when D is an f-divergence for some function ƒ(·), then it generates the metric g^(D_f) = c·g and the connection ∇^(D_f) = ∇^(α), where g is the canonical Fisher information metric, ∇^(α) is the α-connection, c = ƒ′′(1), and α = 3 + 2ƒ′′′(1)/ƒ′′(1).

Examples

The largest and most frequently used class of divergences form the so-called f-divergences, however other types of divergence functions are also encountered in the literature.

f-divergences

This family of divergences are generated through functions f(u), convex on u > 0 and such that f(1) = 0. Then an f-divergence is defined as

$D_{f}(p\parallel q)=\int p(x)f{\bigg (}{\frac {q(x)}{p(x)}}{\bigg )}dx$

Kullback–Leibler divergence:	$D_{{\mathrm {KL}}}(p\parallel q)=\int p(x)\ln \left({\frac {p(x)}{q(x)}}\right)dx$
squared Hellinger distance:	$H^{2}(p,\,q)=2\int {\Big (}{\sqrt {p(x)}}-{\sqrt {q(x)}}\,{\Big )}^{2}dx$
Jeffreys divergence:	$D_{J}(p\parallel q)=\int (p(x)-q(x)){\big (}\ln p(x)-\ln q(x){\big )}dx$
Chernoff's α-divergence:	$D^{{(\alpha )}}(p\parallel q)={\frac {4}{1-\alpha ^{2}}}{\bigg (}1-\int p(x)^{{\frac {1-\alpha }{2}}}q(x)^{{\frac {1+\alpha }{2}}}dx{\bigg )}$
exponential divergence:	$D_{e}(p\parallel q)=\int p(x){\big (}\ln p(x)-\ln q(x){\big )}^{2}dx$
Kagan's divergence:	$D_{{\chi ^{2}}}(p\parallel q)={\frac 12}\int {\frac {(p(x)-q(x))^{2}}{p(x)}}dx$
(α,β)-product divergence:	$D_{{\alpha ,\beta }}(p\parallel q)={\frac {2}{(1-\alpha )(1-\beta )}}\int {\Big (}1-{\Big (}{\tfrac {q(x)}{p(x)}}{\Big )}^{{\!\!{\frac {1-\alpha }{2}}}}{\Big )}{\Big (}1-{\Big (}{\tfrac {q(x)}{p(x)}}{\Big )}^{{\!\!{\frac {1-\beta }{2}}}}{\Big )}p(x)dx$

See also

• Statistical distance

References

1. Eguchi (1985)
2. Eguchi (1992)
3. Matumoto (1993)

• Amari, Shun-ichi; Nagaoka, Hiroshi (2000). Methods of information geometry. Oxford University Press. ISBN 0-8218-0531-2.
• Eguchi, Shinto (1985). "A differential geometric approach to statistical inference on the basis of contrast functionals". Hiroshima mathematical journal. 15 (2): 341–391.
• Eguchi, Shinto (1992). "Geometry of minimum contrast". Hiroshima mathematical journal. 22 (3): 631–647.
• Matumoto, Takao (1993). "Any statistical manifold has a contrast function — on the C³-functions taking the minimum at the diagonal of the product manifold". Hiroshima mathematical journal. 23 (2): 327–332.