Fixed regression in TFactor::partSum
[libdai.git] / include / dai / alldai.h
1 /* Copyright (C) 2006-2008 Joris Mooij [joris dot mooij at tuebingen dot mpg dot de]
2 Radboud University Nijmegen, The Netherlands /
3 Max Planck Institute for Biological Cybernetics, Germany
4
5 This file is part of libDAI.
6
7 libDAI is free software; you can redistribute it and/or modify
8 it under the terms of the GNU General Public License as published by
9 the Free Software Foundation; either version 2 of the License, or
10 (at your option) any later version.
11
12 libDAI is distributed in the hope that it will be useful,
13 but WITHOUT ANY WARRANTY; without even the implied warranty of
14 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 GNU General Public License for more details.
16
17 You should have received a copy of the GNU General Public License
18 along with libDAI; if not, write to the Free Software
19 Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
20 */
21
22
23 /// \file
24 /// \brief Main libDAI header file
25 /// \todo Improve documentation
26
27
28 #ifndef __defined_libdai_alldai_h
29 #define __defined_libdai_alldai_h
30
31
32 #include <string>
33 #include <dai/daialg.h>
34 #include <dai/properties.h>
35 #include <dai/exactinf.h>
36 #ifdef DAI_WITH_BP
37 #include <dai/bp.h>
38 #endif
39 #ifdef DAI_WITH_MF
40 #include <dai/mf.h>
41 #endif
42 #ifdef DAI_WITH_HAK
43 #include <dai/hak.h>
44 #endif
45 #ifdef DAI_WITH_LC
46 #include <dai/lc.h>
47 #endif
48 #ifdef DAI_WITH_TREEEP
49 #include <dai/treeep.h>
50 #endif
51 #ifdef DAI_WITH_JTREE
52 #include <dai/jtree.h>
53 #endif
54 #ifdef DAI_WITH_MR
55 #include <dai/mr.h>
56 #endif
57
58
59 /// Namespace for libDAI
60 namespace dai {
61
62
63 /// Constructs a new approximate inference algorithm.
64 /** \param name The name of the approximate inference algorithm (should be one of the names in DAINames).
65 * \param fg The FactorGraph that the algorithm should be applied to.
66 * \param opts A PropertySet specifying the options for the algorithm.
67 * \return Returns a pointer to the new InfAlg object; it is the responsibility of the caller to delete it later.
68 */
69 InfAlg *newInfAlg( const std::string &name, const FactorGraph &fg, const PropertySet &opts );
70
71
72 /// Contains the names of all approximate inference algorithms compiled into libDAI.
73 static const char* DAINames[] = {
74 ExactInf::Name,
75 #ifdef DAI_WITH_BP
76 BP::Name,
77 #endif
78 #ifdef DAI_WITH_MF
79 MF::Name,
80 #endif
81 #ifdef DAI_WITH_HAK
82 HAK::Name,
83 #endif
84 #ifdef DAI_WITH_LC
85 LC::Name,
86 #endif
87 #ifdef DAI_WITH_TREEEP
88 TreeEP::Name,
89 #endif
90 #ifdef DAI_WITH_JTREE
91 JTree::Name,
92 #endif
93 #ifdef DAI_WITH_MR
94 MR::Name,
95 #endif
96 ""
97 };
98
99
100 } // end of namespace dai
101
102
103 /** \mainpage libDAI reference manual
104 * \author Joris Mooij
105 * \version git HEAD
106 * \date October 8, 2008
107 *
108 * \section about About libDAI
109 * libDAI is a free/open source C++ library (licensed under GPL) that provides
110 * implementations of various (approximate) inference methods for discrete
111 * graphical models. libDAI supports arbitrary factor graphs with discrete
112 * variables; this includes discrete Markov Random Fields and Bayesian
113 * Networks.
114 *
115 * The library is targeted at researchers; to be able to use the library, a
116 * good understanding of graphical models is needed.
117 *
118 * \section limitations Limitations
119 * libDAI is not intended to be a complete package for approximate inference.
120 * Instead, it should be considered as an "inference engine", providing
121 * various inference methods. In particular, it contains no GUI, currently
122 * only supports its own file format for input and output (although support
123 * for standard file formats may be added later), and provides very limited
124 * visualization functionalities.
125 *
126 * \section features Features
127 * Currently, libDAI supports the following (approximate) inference methods:
128 * - Exact inference by brute force enumeration;
129 * - Exact inference by junction-tree methods;
130 * - Mean Field;
131 * - Loopy Belief Propagation [\ref KFL01];
132 * - Tree Expectation Propagation [\ref MiQ04];
133 * - Generalized Belief Propagation [\ref YFW05];
134 * - Double-loop GBP [\ref HAK03];
135 * - Various variants of Loop Corrected Belief Propagation
136 * [\ref MoK07, \ref MoR05].
137 *
138 * \section language Why C++?
139 * Because libDAI is implemented in C++, it is very fast compared with
140 * implementations in MatLab (a factor 1000 faster is not uncommon).
141 * libDAI does provide a MatLab interface for easy integration with MatLab.
142 *
143 * \section quickstart Quick start
144 * An example program illustrating basic usage of libDAI is given in examples/example.cpp.
145 */
146
147 /// \example example.cpp
148
149 /** \page Bibliography
150 * \section Bibliograpy
151 * \anchor KFL01 \ref KFL01
152 * F. R. Kschischang and B. J. Frey and H.-A. Loeliger (2001):
153 * "Factor Graphs and the Sum-Product Algorithm",
154 * <em>IEEE Transactions on Information Theory</em> 47(2):498-519.
155 * http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=910572
156 *
157 * \anchor MiQ04 \ref MiQ04
158 * T. Minka and Y. Qi (2004):
159 * "Tree-structured Approximations by Expectation Propagation",
160 * <em>Advances in Neural Information Processing Systems</em> (NIPS) 16.
161 * http://books.nips.cc/papers/files/nips16/NIPS2003_AA25.pdf
162 *
163 * \anchor MoR05 \ref MoR05
164 * A. Montanari and T. Rizzo (2005):
165 * "How to Compute Loop Corrections to the Bethe Approximation",
166 * <em>Journal of Statistical Mechanics: Theory and Experiment</em>
167 * 2005(10)-P10011.
168 * http://stacks.iop.org/1742-5468/2005/P10011
169 *
170 * \anchor YFW05 \ref YFW05
171 * J. S. Yedidia and W. T. Freeman and Y. Weiss (2005):
172 * "Constructing Free-Energy Approximations and Generalized Belief Propagation Algorithms",
173 * <em>IEEE Transactions on Information Theory</em>
174 * 51(7):2282-2312.
175 * http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1459044
176 *
177 * \anchor HAK03 \ref HAK03
178 * T. Heskes and C. A. Albers and H. J. Kappen (2003):
179 * "Approximate Inference and Constrained Optimization",
180 * <em>Proceedings of the 19th Annual Conference on Uncertainty in Artificial Intelligence (UAI-03)</em> pp. 313-320.
181 * http://www.snn.ru.nl/reports/Heskes.uai2003.ps.gz
182 *
183 * \anchor MoK07 \ref MoK07
184 * J. M. Mooij and H. J. Kappen (2007):
185 * "Loop Corrections for Approximate Inference on Factor Graphs",
186 * <em>Journal of Machine Learning Research</em> 8:1113-1143.
187 * http://www.jmlr.org/papers/volume8/mooij07a/mooij07a.pdf
188 *
189 * \anchor MoK07b \ref MoK07b
190 * J. M. Mooij and H. J. Kappen (2007):
191 * "Sufficient Conditions for Convergence of the Sum-Product Algorithm",
192 * <em>IEEE Transactions on Information Theory</em> 53(12):4422-4437.
193 * http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4385778
194 */
195
196
197 #endif