conditionalbayesprocess.hpp

Go to the documentation of this file.

/*
-------------------------------------------------------------------------
   This file is part of BayesOpt, an efficient C++ library for 
   Bayesian optimization.

   Copyright (C) 2011-2015 Ruben Martinez-Cantin <rmcantin@unizar.es>
 
   BayesOpt is free software: you can redistribute it and/or modify it 
   under the terms of the GNU Affero General Public License as published by
   the Free Software Foundation, either version 3 of the License, or
   (at your option) any later version.

   BayesOpt is distributed in the hope that it will be useful, but 
   WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU Affero General Public License for more details.

   You should have received a copy of the GNU Affero General Public License
   along with BayesOpt.  If not, see <http://www.gnu.org/licenses/>.
------------------------------------------------------------------------
*/


#ifndef  _CONDITIONAL_BAYES_PROCESS_HPP_
#define  _CONDITIONAL_BAYES_PROCESS_HPP_

#include "kernelregressor.hpp"

namespace bayesopt
{

  class ConditionalBayesProcess: public KernelRegressor
  {
  public:
    ConditionalBayesProcess(size_t dim, Parameters parameters, 
                const Dataset& data, 
                MeanModel& mean, randEngine& eng);
    virtual ~ConditionalBayesProcess();

    virtual ProbabilityDistribution* prediction(const vectord &query) = 0;
                 
    double evaluate(const vectord &x);

    double evaluateKernelParams();


  protected:
    virtual double negativeTotalLogLikelihood() = 0;


    virtual double negativeLogLikelihood() = 0;

  private:
    double negativeCrossValidation();

  };


  // WARNING!! evaluateKernelParams models return the NEGATIVE
  // log-score (likelihood, LOO, MAP, etc.). 
  inline double ConditionalBayesProcess::evaluate(const vectord& x)
  { 
    setHyperParameters(x);
    return evaluateKernelParams();
  };


} //namespace bayesopt

#endif