Stan  2.10.0
probability, sampling & optimization
adapt_softabs_xhmc.hpp
Go to the documentation of this file.
1 #ifndef STAN_MCMC_HMC_XHMC_ADAPT_SOFTABS_XHMC_HPP
2 #define STAN_MCMC_HMC_XHMC_ADAPT_SOFTABS_XHMC_HPP
3 
7 
8 namespace stan {
9  namespace mcmc {
15  template <class Model, class BaseRNG>
16  class adapt_softabs_xhmc: public softabs_xhmc<Model, BaseRNG>,
17  public stepsize_adapter {
18  public:
19  adapt_softabs_xhmc(const Model& model, BaseRNG& rng)
20  : softabs_xhmc<Model, BaseRNG>(model, rng) {}
21 
23 
25  sample& init_sample,
28  sample s
30  info_writer, error_writer);
31 
32  if (this->adapt_flag_)
34  s.accept_stat());
35 
36  return s;
37  }
38 
42  }
43  };
44 
45  } // mcmc
46 } // stan
47 #endif
void complete_adaptation(double &epsilon)
Exhausive Hamiltonian Monte Carlo (XHMC) with multinomial sampling with a Gaussian-Riemannian disinte...
sample transition(sample &init_sample, interface_callbacks::writer::base_writer &info_writer, interface_callbacks::writer::base_writer &error_writer)
Definition: base_xhmc.hpp:88
double accept_stat() const
Definition: sample.hpp:41
Probability, optimization and sampling library.
void learn_stepsize(double &epsilon, double adapt_stat)
adapt_softabs_xhmc(const Model &model, BaseRNG &rng)
sample transition(sample &init_sample, interface_callbacks::writer::base_writer &info_writer, interface_callbacks::writer::base_writer &error_writer)
base_writer is an abstract base class defining the interface for Stan writer callbacks.
Definition: base_writer.hpp:20
virtual void disengage_adaptation()
Exhausive Hamiltonian Monte Carlo (XHMC) with multinomial sampling with a Gaussian-Riemannian disinte...
stepsize_adaptation stepsize_adaptation_

     [ Stan Home Page ] © 2011–2016, Stan Development Team.