Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Calculating the normalising constant of the Bingham distribution on the sphere using the holonomic gradient method

Abstract

In this paper we implement the holonomic gradient method to exactly compute the normalising constant of Bingham distributions. This idea is originally applied for general Fisher–Bingham distributions in Nakayama et al. (Adv. Appl. Math. 47:639–658, 2011). In this paper we explicitly apply this algorithm to show the exact calculation of the normalising constant; derive explicitly the Pfaffian system for this parametric case; implement the general approach for the maximum likelihood solution search and finally adjust the method for degenerate cases, namely when the parameter values have multiplicities.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2

References

  1. Barndorff-Nielsen, O.: Information and Exponential Families. Wiley Series in Probability and Mathematical Statistics. Wiley, New York (1978)

  2. Feller, W.: An Introduction to Probability Theory and Its Applications vol. 2. Wiley, New York (1971)

  3. Hashiguchi, H., Numata, Y., Takayama, N., Takemura, A.: Holonomic gradient method for the distribution function of the largest root of a Wishart matrix. J. Multivar. Anal. 117, 296–312 (2013)

  4. Kent, J.T.: The complex Bingham distribution and shape analysis. J. R. Stat. Soc. 56, 285–289 (1994)

  5. Koyama, T.: A holonomic ideal annihilating the Fisher–Bingham integral (2011). arXiv:1104.1411

  6. Koyama, T., Nakayama, H., Nishiyama, K., Takayama, N.: Holonomic gradient descent for the Fisher–Bingham distribution on the n-dimensional sphere (2012a). arXiv:1201.3239

  7. Koyama, T., Nakayama, H., Nishiyama, K., Takayama, N.: The holonomic rank of the Fisher–Bingham system of differential equations (2012b). arXiv:1205.6144

  8. Kume, A., Wood, A.T.A.: Saddlepoint approximations for the Bingham and Fisher–Bingham normalising constants. Biometrika 92, 465–476 (2005)

  9. Kume, A., Wood, A.T.A.: On the derivatives of the normalising constant of the Bingham distribution. Stat. Probab. Lett. 77, 832–837 (2007)

  10. Mardia, K.V., Jupp, P.E.: Directional Statistics. Wiley Series in Probability and Statistics. Wiley, Chichester (2000). ISBN 0-471-95333-4

  11. Nakayama, H., Nishiyama, K., Noro, M., Ohara, K., Sei, T., Takayama, N., Takemura, A.: Holonomic gradient descent and its application to the Fisher–Bingham integral. Adv. Appl. Math. 47, 639–658 (2011)

  12. Sei, T., Shibata, H., Takemura, A., Ohara, K., Takayama, N.: Properties and applications of Fisher distribution on the rotation group. J. Multivar. Anal. 116, 440–455 (2013)

  13. Sun, W., Yuan, Y.-X.: Optimization Theory and Methods. Springer, New York (2006)

  14. Takayama, N.: Propagation of singularities of solutions of the Euler–Darboux equation and a global structure of the space of holonomic functions I. Funkc. Ekvacioj 35, 343–403 (1992)

Download references

Acknowledgements

The first author is supported by JSPS Institutional Program for Young Researcher Overseas Visits.

Author information

Correspondence to Tomonari Sei.

Appendices

Appendix A: One-dimensional representation

First we briefly describe derivation of the one-dimensional representation (3) according to Kume and Wood (2005). Note that the parameter λ i in their paper is our −θ i . Consider p independent normal random variables x i N(0,(−2θ i )−1), where θ i <0 for all i. Then the marginal density of \(r=\sum_{i=1}^{p}x_{i}^{2}\) is directly calculated as

$$\begin{aligned} f(r) = \frac{r^{p/2-1}\prod_k\sqrt{-\theta_k}}{\varGamma (p/2)}\frac{c(r\boldsymbol{\theta})}{c(\boldsymbol{0})}. \end{aligned}$$
(26)

On the other hand, the characteristic function of r is

$$\begin{aligned} \phi(s) = E\bigl[e^{is\sum_ix_i^2}\bigr] = \prod_k \sqrt{\frac{-\theta_k}{-\theta_k-is}}. \end{aligned}$$
(27)

In general, the density function is represented by its characteristic function as

$$\begin{aligned} f(r) = \frac{1}{2\pi}\lim_{\epsilon\to0}\int_{-\infty}^{\infty} \phi(s)e^{-is r-\epsilon s^2/2}ds \end{aligned}$$
(28)

at arbitrary continuous point of f (see e.g. Feller 1971). By combining Eqs. (26) to (28), we have

$$\begin{aligned} c(\boldsymbol{\theta}) &= \frac{\varGamma(p/2)c(\boldsymbol{0})}{\prod_k\sqrt{-\theta_k}}f(1) \\ &= \frac{c(\boldsymbol{0})}{2\pi}\lim_{\epsilon\to0}\int_{-\infty}^{\infty} \frac{1}{\prod_k\sqrt{-\theta_k-is}}e^{-is-\epsilon s^2/2}ds. \end{aligned}$$

Note that this expression holds for any p≥2. If p≥3, then

$$\begin{aligned} c(\boldsymbol{\theta}) &= \frac{c(\boldsymbol{0})}{2\pi}\int_{-\infty}^{\infty} \frac{1}{\prod_k\sqrt{-\theta_k-is}}e^{-is}ds \end{aligned}$$

since \(|\prod_{k=1}^{p}(-\theta_{k}-is)^{-1/2}|\) is integrable over (−∞,∞). By analytic continuation with respect to s, we obtain

$$\begin{aligned} c(\boldsymbol{\theta}) &= \frac{c(\boldsymbol{0})}{2\pi}\int_{-\infty}^{\infty} \frac{1}{\prod_k\sqrt{-\theta_k-t_0-is}}e^{-t_0-is}ds \end{aligned}$$
(29)

for any real number t 0 less than min k (−θ k ). Even if some θ i ’s are not negative, Eq. (29) still holds due to analytic continuation with respect to θ, as long as t 0<min k (−θ k ). Hence we obtain (3).

Appendix B: Truncation error of the power series

We derive the power series expansion of c(θ) and evaluate the truncation error according to Koyama et al. (2012a). Let θ(ϕ,d)=(ϕ 1,…,ϕ 1,…,ϕ q ,…,ϕ q ) be a parameter vector with multiplicities d=(d 1,…,d q ). By Kume and Wood (2007), we have

$$\begin{aligned} c\bigl(\boldsymbol{\theta}(\boldsymbol{\phi},\boldsymbol{d})\bigr) =& \int _{S^{p-1}} e^{\sum_{i=1}^p \theta_i(\boldsymbol{\phi },\boldsymbol{d}) x_i^2} d\boldsymbol{x} = c(\boldsymbol{0})\sum _{k_1=0}^{\infty}\cdots \sum _{k_q=0}^{\infty} \frac{\phi_1^{k_1}\cdots\phi_q^{k_q}}{k_1!\cdots k_q!} \frac{\prod_i \varGamma(k_i+d_i/2)}{\varGamma(\sum_i (k_i+d_i/2))} \frac{\varGamma(\sum_i d_i/2)}{\prod_i\varGamma(d_i/2)}. \end{aligned}$$

Let

$$c_N\bigl(\boldsymbol{\theta}(\boldsymbol{\phi},\boldsymbol{d})\bigr) := c(\boldsymbol{0}) \sum_{k_1+\cdots+k_q < N} \frac{\phi_1^{k_1}\cdots\phi_q^{k_q}}{k_1!\cdots k_q!} \frac{\prod_i \varGamma(k_i+d_i/2)}{\varGamma(\sum_i (k_i+d_i/2))} \frac{\varGamma(\sum_i d_i/2)}{\prod_i\varGamma(d_i/2)}. $$

Then the truncation error is evaluated as

$$\begin{aligned} \frac{|c(\boldsymbol{\theta}(\boldsymbol{\phi},\boldsymbol{d})) - c_N(\boldsymbol{\theta}(\boldsymbol{\phi},\boldsymbol {d}))|}{c(\boldsymbol{0})} \leq&\sum_{k_1+\cdots+k_q\geq N} \frac{|\phi_1|^{k_1}\cdots|\phi_q|^{k_q}}{k_1!\cdots k_q!} \frac{\prod_i\varGamma(k_i+d_i/2)}{\varGamma(\sum_i(k_i+d_i/2))} \frac{\varGamma(\sum_i d_i/2)}{\prod_i\varGamma(d_i/2)} \\ \leq&\sum_{k_1+\cdots+k_q\geq N} \frac{|\phi_1|^{k_1}\cdots|\phi_q|^{k_q}}{k_1!\cdots k_q!} \\ =& \sum_{n=N}^{\infty} \frac{1}{n!}\sum _{k_1+\cdots+k_q=n} \frac{n!}{k_1!\cdots k_q!} |\phi_1|^{k_1} \cdots|\phi_q|^{k_q} = \sum_{n=N}^{\infty} \frac{\|\boldsymbol{\phi}\|_1^n}{n!} \\ \leq&\frac{\|\boldsymbol{\phi}\|_1^N}{N!} \sum_{n=N}^{\infty} \frac{\|\boldsymbol{\phi}\|_1^{n-N}}{(N+1)^{n-N}} = \frac{\|\boldsymbol{\phi}\|_1^N}{N!} \frac{N+1}{N+1-\|\boldsymbol{\phi}\|_1}. \end{aligned}$$

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Sei, T., Kume, A. Calculating the normalising constant of the Bingham distribution on the sphere using the holonomic gradient method. Stat Comput 25, 321–332 (2015). https://doi.org/10.1007/s11222-013-9434-0

Download citation

Keywords

  • Bingham distributions
  • Directional statistics
  • Holonomic functions