gp.hpp 10.4 KB
Newer Older
1
2
#ifndef LIMBO_MODEL_GP_HPP
#define LIMBO_MODEL_GP_HPP
3

4
#include <iostream>
5
#include <cassert>
6
#include <limits>
7
#include <vector>
8

9
10
11
12
#include <Eigen/Core>
#include <Eigen/LU>
#include <Eigen/Cholesky>

13
namespace limbo {
14
    namespace model {
15
        template <typename Params, typename KernelFunction, typename MeanFunction>
16
        class GP {
17
18
19
20
21
22
23
        public:
            GP() : _dim_in(-1), _dim_out(-1) {}
            // useful because the model might be created  before having samples
            GP(int dim_in, int dim_out)
                : _dim_in(dim_in), _dim_out(dim_out), _kernel_function(dim_in), _mean_function(dim_out) {}

            void compute(const std::vector<Eigen::VectorXd>& samples,
24
                const std::vector<Eigen::VectorXd>& observations, double noise,
25
26
                const std::vector<Eigen::VectorXd>& bl_samples = std::vector<Eigen::VectorXd>())
            {
27
                if (_dim_in == -1) {
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
                    assert(samples.size() != 0);
                    assert(observations.size() != 0);
                    assert(samples.size() == observations.size());
                    _dim_in = samples[0].size();
                    _dim_out = observations[0].size();
                }

                _samples = samples;

                _observations.resize(observations.size(), observations[0].size());
                for (int i = 0; i < _observations.rows(); ++i)
                    _observations.row(i) = observations[i];

                _mean_observation.resize(_dim_out);
                for (int i = 0; i < _observations.cols(); i++)
                    _mean_observation(i) = _observations.col(i).sum() / _observations.rows();

                _noise = noise;

                _bl_samples = bl_samples;

                _compute_obs_mean();
                _compute_kernel();
            }

            // return mu, sigma (unormaliz)
54
            std::tuple<Eigen::VectorXd, double> query(const Eigen::VectorXd& v) const
55
56
57
58
59
60
61
62
63
64
65
66
67
            {
                if (_samples.size() == 0 && _bl_samples.size() == 0)
                    return std::make_tuple(_mean_function(v, *this),
                        sqrt(_kernel_function(v, v)));

                if (_samples.size() == 0)
                    return std::make_tuple(_mean_function(v, *this),
                        _sigma(v, _compute_k_bl(v, _compute_k(v))));

                Eigen::VectorXd k = _compute_k(v);
                return std::make_tuple(_mu(v, k), _sigma(v, _compute_k_bl(v, k)));
            }

68
            Eigen::VectorXd mu(const Eigen::VectorXd& v) const
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
            {
                if (_samples.size() == 0)
                    return _mean_function(v, *this);
                return _mu(v, _compute_k(v));
            }

            double sigma(const Eigen::VectorXd& v) const
            {
                if (_samples.size() == 0 && _bl_samples.size() == 0)
                    return sqrt(_kernel_function(v, v));
                return _sigma(v, _compute_k_bl(v, _compute_k(v)));
            }

            int dim_in() const
            {
                assert(_dim_in != -1); // need to compute first !
                return _dim_in;
            }

            int dim_out() const
            {
                assert(_dim_out != -1); // need to compute first !
                return _dim_out;
            }

            const KernelFunction& kernel_function() const { return _kernel_function; }

96
97
            KernelFunction& kernel_function() { return _kernel_function; }

98
99
            const MeanFunction& mean_function() const { return _mean_function; }

100
101
            MeanFunction& mean_function() { return _mean_function; }

102
            Eigen::VectorXd max_observation() const
103
104
105
106
107
108
109
            {
                if (_observations.cols() > 1)
                    std::cout << "WARNING max_observation with multi dim_inensional "
                                 "observations doesn't make sense" << std::endl;
                return _observations.maxCoeff();
            }

110
            Eigen::VectorXd mean_observation() const
111
            {
112
                // TO-DO: Check if _dim_out is correct?!
113
                return _samples.size() > 0 ? _mean_observation
114
                                           : Eigen::VectorXd::Zero(_dim_out);
115
116
117
118
            }

            const Eigen::MatrixXd& mean_vector() const { return _mean_vector; }

119
            const Eigen::MatrixXd& obs_mean() const { return _obs_mean; }
120

121
122
123
124
            int nb_samples() const { return _samples.size(); }

            int nb_bl_samples() const { return _bl_samples.size(); }

125
126
127
128
129
130
131
132
133
134
            void update()
            {
                this->_compute_obs_mean(); // ORDER MATTERS
                this->_compute_kernel();
            }

            float get_lik() const { return _lik; }

            void set_lik(const float& lik) { _lik = lik; }

135
            const Eigen::LLT<Eigen::MatrixXd>& llt() const { return _llt; }
136

137
            const Eigen::MatrixXd& alpha() const { return _alpha; }
138

139
            const std::vector<Eigen::VectorXd>& samples() const { return _samples; }
140

141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
        protected:
            int _dim_in;
            int _dim_out;

            KernelFunction _kernel_function;
            MeanFunction _mean_function;

            std::vector<Eigen::VectorXd> _samples;
            Eigen::MatrixXd _observations;
            std::vector<Eigen::VectorXd> _bl_samples; // black listed samples
            Eigen::MatrixXd _mean_vector;
            Eigen::MatrixXd _obs_mean;

            double _noise;
            Eigen::MatrixXd _alpha;
156
            Eigen::VectorXd _mean_observation;
157
158
159
160
161
162
163

            Eigen::MatrixXd _kernel;
            // Eigen::MatrixXd _inverted_kernel;
            Eigen::MatrixXd _l_matrix;
            Eigen::LLT<Eigen::MatrixXd> _llt;
            Eigen::MatrixXd _inv_bl_kernel;

164
165
            float _lik;

166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
            void _compute_obs_mean()
            {
                _mean_vector.resize(_samples.size(), _dim_out);
                for (int i = 0; i < _mean_vector.rows(); i++)
                    _mean_vector.row(i) = _mean_function(_samples[i], *this);
                _obs_mean = _observations - _mean_vector;
            }

            void _compute_kernel()
            {
                // O(n^2) [should be negligible]
                _kernel.resize(_samples.size(), _samples.size());
                for (int i = 0; i < _samples.size(); i++)
                    for (int j = 0; j < _samples.size(); ++j)
                        _kernel(i, j) = _kernel_function(_samples[i], _samples[j]) + ((i == j) ? _noise : 0); // noise only on the diagonal

                // O(n^3)
                //  _inverted_kernel = _kernel.inverse();

                _llt = Eigen::LLT<Eigen::MatrixXd>(_kernel);

                // alpha = K^{-1} * this->_obs_mean;
                _alpha = _llt.matrixL().solve(_obs_mean);
                _llt.matrixL().adjoint().solveInPlace(_alpha);
                if (_bl_samples.size() == 0)
                    return;

                Eigen::MatrixXd A1 = Eigen::MatrixXd::Identity(this->_samples.size(), this->_samples.size());
                _llt.matrixL().solveInPlace(A1);
                _llt.matrixL().transpose().solveInPlace(A1);
                _inv_bl_kernel.resize(_samples.size() + _bl_samples.size(),
                    _samples.size() + _bl_samples.size());

                Eigen::MatrixXd B(_samples.size(), _bl_samples.size());
                for (size_t i = 0; i < _samples.size(); i++)
                    for (size_t j = 0; j < _bl_samples.size(); ++j)
                        B(i, j) = _kernel_function(_samples[i], _bl_samples[j]);

                Eigen::MatrixXd D(_bl_samples.size(), _bl_samples.size());
                for (size_t i = 0; i < _bl_samples.size(); i++)
                    for (size_t j = 0; j < _bl_samples.size(); ++j)
                        D(i, j) = _kernel_function(_bl_samples[i], _bl_samples[j]) + ((i == j) ? _noise : 0);

                Eigen::MatrixXd comA = (D - B.transpose() * A1 * B);
                Eigen::LLT<Eigen::MatrixXd> llt_bl(comA);
                Eigen::MatrixXd comA1 = Eigen::MatrixXd::Identity(_bl_samples.size(), _bl_samples.size());
                llt_bl.matrixL().solveInPlace(comA1);
                llt_bl.matrixL().transpose().solveInPlace(comA1);

                // fill the matrix block wise
                _inv_bl_kernel.block(0, 0, _samples.size(), _samples.size()) = A1 + A1 * B * comA1 * B.transpose() * A1;
                _inv_bl_kernel.block(0, _samples.size(), _samples.size(),
                    _bl_samples.size()) = -A1 * B * comA1;
                _inv_bl_kernel.block(_samples.size(), 0, _bl_samples.size(),
                    _samples.size()) = _inv_bl_kernel.block(0, _samples.size(), _samples.size(),
                                                          _bl_samples.size()).transpose();
                _inv_bl_kernel.block(_samples.size(), _samples.size(), _bl_samples.size(),
                    _bl_samples.size()) = comA1;
            }

226
            Eigen::VectorXd _mu(const Eigen::VectorXd& v, const Eigen::VectorXd& k) const
227
228
229
230
231
232
233
            {
                return (k.transpose() * _alpha) + _mean_function(v, *this).transpose();
            }

            double _sigma(const Eigen::VectorXd& v, const Eigen::VectorXd& k) const
            {
                double res;
234
                if (_bl_samples.size() == 0) {
235
236
237
                    Eigen::VectorXd z = _llt.matrixL().solve(k);
                    res = _kernel_function(v, v) - z.dot(z);
                }
238
                else {
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
                    res = _kernel_function(v, v) - k.transpose() * _inv_bl_kernel * k;
                }

                return (res <= std::numeric_limits<double>::epsilon()) ? 0 : res;
            }

            Eigen::VectorXd _compute_k(const Eigen::VectorXd& v) const
            {
                Eigen::VectorXd k(_samples.size());
                for (int i = 0; i < k.size(); i++)
                    k[i] = _kernel_function(_samples[i], v);
                return k;
            }

            Eigen::VectorXd _compute_k_bl(const Eigen::VectorXd& v,
                const Eigen::VectorXd& k) const
            {
256
                if (_bl_samples.size() == 0) {
257
258
259
260
261
262
263
264
265
266
267
268
                    return k;
                }

                Eigen::VectorXd k_bl(_samples.size() + _bl_samples.size());

                k_bl.head(_samples.size()) = k;
                for (size_t i = 0; i < _bl_samples.size(); i++)
                    k_bl[i + this->_samples.size()] = this->_kernel_function(_bl_samples[i], v);
                return k_bl;
            }
        };
    }
269
}
270

271
#endif