version 1.2, 2014/04/03 07:34:30 |
version 1.3, 2017/03/30 07:01:30 |
|
|
$OpenXM: OpenXM/src/asir-contrib/packages/doc/nk_fb_gen_c/nk_fb_gen_c.oxg,v 1.1 2014/03/27 05:24:28 takayama Exp $ |
$OpenXM: OpenXM/src/asir-contrib/packages/doc/nk_fb_gen_c/nk_fb_gen_c.oxg,v 1.2 2014/04/03 07:34:30 takayama Exp $ |
test1.c, test1.h $B$O$3$N%W%m%0%i%`$G@8@.$5$l$?Nc(B. data, $B=i4|CM$O$9$G$K@_Dj:Q(B. |
test1.c, test1.h はこのプログラムで生成された例. data, 初期値はすでに設定済. |
/* $B$^$@=q$$$F$J$$(B. |
/* まだ書いてない. |
begin: include| |
begin: include| |
|
|
@include nk_fb_gen_c_intro.ja |
@include nk_fb_gen_c_intro.ja |
|
|
end: |
end: |
*/ |
*/ |
|
|
/* $B$^$@=q$$$F$J$$(B. |
/* まだ書いてない. |
begin: include| |
begin: include| |
|
|
@include nk_fb_gen_c_intro.en |
@include nk_fb_gen_c_intro.en |
|
|
|
|
/*&usage-ja |
/*&usage-ja |
begin: nk_fb_gen_c.gen_c(N) |
begin: nk_fb_gen_c.gen_c(N) |
{N} $B<!85(B Fisher-Bingham $BJ,I[$K$D$$$F$N:GL`?dDj$r(B HGD $BK!(B(holonomic gradient descent) $B$G$d$k$?$a$N(B C $B$N%W%m%0%i%`$r@8@.$9$k(B. |
{N} 次元 Fisher-Bingham 分布についての最尤推定を HGD 法(holonomic gradient descent) でやるための C のプログラムを生成する. |
description: |
description: |
$B$3$N4X?t$K$h$j(B, testN.c, testN.h $B$J$kFs$D$N(B C $B$N%W%m%0%i%`$,@8@.$5$l$k(B. |
この関数により, testN.c, testN.h なる二つの C のプログラムが生成される. |
testN.c $B$K%G!<%?(B, $B:GL`?dDjC5:wMQ$N%Q%i%a!<%?=i4|CM$r@_Dj$9$k(B. |
testN.c にデータ, 最尤推定探索用のパラメータ初期値を設定する. |
$B%3%^%s%I(B |
コマンド |
@quotation |
@quotation |
@code{gcc testN.c $OpenXM_HOME/lib/libko_fb.a -lgsl -lblas } |
@code{gcc testN.c $OpenXM_HOME/lib/libko_fb.a -lgsl -lblas } |
@end quotation |
@end quotation |
$B$G<B9T2DG=7A<0$N%U%!%$%k$r:n@.$9$k(B. @* |
で実行可能形式のファイルを作成する. @* |
$B$J$*(B, |
なお, |
libko_fb.a $B$O(B @file{OpenXM/src/hgm/fisher-bingham/src/} $B$G(B @code{make install} $B$9$k$3$H$K$h$j@8@.$5$l$k(B. |
libko_fb.a は @file{OpenXM/src/hgm/fisher-bingham/src/} で @code{make install} することにより生成される. |
$B$^$?%7%9%F%`$K$O(B gsl $B$,%$%s%9%H!<%k$5$l$F$$$J$$$H$$$1$J$$(B. |
またシステムには gsl がインストールされていないといけない. |
@file{OpenXM/src/hgm/fisher-bingham/src/Testdata} $B$K%5%s%W%k$N(B |
@file{OpenXM/src/hgm/fisher-bingham/src/Testdata} にサンプルの |
$B%G!<%?(B, $B:GL`?dDjC5:wMQ$N%Q%i%a!<%?=i4|CM$,$"$k(B. @* |
データ, 最尤推定探索用のパラメータ初期値がある. @* |
testN.h $B$N(B @code{#define MULTIMIN_FDFMINIMIZER_TYPE} $B$G(B gsl $B$N$I$N:GE,2=4X?t$r8F$S=P$9$+JQ99$G$-$k(B. |
testN.h の @code{#define MULTIMIN_FDFMINIMIZER_TYPE} で gsl のどの最適化関数を呼び出すか変更できる. |
testN.h $B$N(B @code{#define ODEIV_STEP_TYPE} $B$G(B gsl $B$N$I$N>oHyJ,J}Dx<0?tCM2r@O4X?t$r8F$S=P$9$+JQ99$G$-$k(B. @* |
testN.h の @code{#define ODEIV_STEP_TYPE} で gsl のどの常微分方程式数値解析関数を呼び出すか変更できる. @* |
$B%"%k%4%j%:%`$N>\:Y$O(B, |
アルゴリズムの詳細は, |
T. Koyama, H. Nakayama, K. Nishiyama, N. Takayama, Holonomic Gradient Descent for the Fisher-Bingham Distribution on the d-dimensional Sphere, Computational Statistics (2013), |
T. Koyama, H. Nakayama, K. Nishiyama, N. Takayama, Holonomic Gradient Descent for the Fisher-Bingham Distribution on the d-dimensional Sphere, Computational Statistics (2013), |
@url{http://dx.doi.org/10.1007/s00180-013-0456-z} |
@url{http://dx.doi.org/10.1007/s00180-013-0456-z} |
$B$r;2>H(B. @* |
を参照. @* |
Authors; T.Koyama, H.Nakayama, K.Nishiyama, N.Takayama. |
Authors; T.Koyama, H.Nakayama, K.Nishiyama, N.Takayama. |
example: |
example: |
[1854] load("nk_fb_gen_c.rr"); |
[1854] load("nk_fb_gen_c.rr"); |
[2186] nk_fb_gen_c.gen_c(1); S^1 $B$NLdBj$r2r$/(B program $B$r@8@.(B. |
[2186] nk_fb_gen_c.gen_c(1); S^1 の問題を解く program を生成. |
generate test1.h |
generate test1.h |
generate test1.c |
generate test1.c |
1 |
1 |
Line 50 $ emacs test1.c & |
|
Line 50 $ emacs test1.c & |
|
|
|
|
|
Write data here. |
Write data here. |
$B$H%3%a%s%H$K=q$+$l$F$$$k$H$3$m$N8e(B |
とコメントに書かれているところの後 |
$B$K(B $(OpenXM_HOME)/src/hgm/fisher-bingham/Testdata/s1_wind_data.h $B$rA^F~(B. |
に $(OpenXM_HOME)/src/hgm/fisher-bingham/Testdata/s1_wind_data.h を挿入. |
$BJ]B8=*N;(B. |
保存終了. |
|
|
$ gcc test1.c $OpenXM_HOME/lib/libko_fb.a -lgsl -lblas |
$ gcc test1.c $OpenXM_HOME/lib/libko_fb.a -lgsl -lblas |
$ ./a.out |
$ ./a.out |
Line 63 grad ; 0.005644 -0.033429 -0.005644 0.045820 0.047695 |
|
Line 63 grad ; 0.005644 -0.033429 -0.005644 0.045820 0.047695 |
|
norm(grad) ; 0.074535 |
norm(grad) ; 0.074535 |
--- snip |
--- snip |
|
|
$B$3$3$G(B, points $B$,(B parameter x11,x12,x22,y1,y2 $B$N?dDjCM(B. |
ここで, points が parameter x11,x12,x22,y1,y2 の推定値. |
Value 3.4421 $B$,(B $BL`EYCM$N5U?t$G(B, $B$3$l$,:G>.2=$5$l$F$$$k(B. |
Value 3.4421 が 尤度値の逆数で, これが最小化されている. |
end: |
end: |
*/ |
*/ |
|
|