apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-07 11:02:38 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

[model] optimizer can now be an optimizer instance, instead of a string

Browse source
This commit is contained in:
mzwiessele 2014-06-19 12:06:39 -07:00
parent 1e006f63b5
commit eaa18e3512
1 changed files with 12 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

22
GPy/core/model.py
View file

@ -118,12 +118,12 @@ class Model(Parameterized):
""" """
The objective function for the given algorithm. The objective function for the given algorithm.
This function is the true objective, which wants to be minimized. This function is the true objective, which wants to be minimized.
Note that all parameters are already set and in place, so you just need Note that all parameters are already set and in place, so you just need
to return the objective function here. to return the objective function here.
For probabilistic models this is the negative log_likelihood For probabilistic models this is the negative log_likelihood
(including the MAP prior), so we return it here. If your model is not (including the MAP prior), so we return it here. If your model is not
probabilistic, just return your objective to minimize here! probabilistic, just return your objective to minimize here!
""" """
return -float(self.log_likelihood()) - self.log_prior() return -float(self.log_likelihood()) - self.log_prior()
@ -131,18 +131,18 @@ class Model(Parameterized):
def objective_function_gradients(self): def objective_function_gradients(self):
""" """
The gradients for the objective function for the given algorithm. The gradients for the objective function for the given algorithm.
The gradients are w.r.t. the *negative* objective function, as The gradients are w.r.t. the *negative* objective function, as
this framework works with *negative* log-likelihoods as a default. this framework works with *negative* log-likelihoods as a default.
You can find the gradient for the parameters in self.gradient at all times. You can find the gradient for the parameters in self.gradient at all times.
This is the place, where gradients get stored for parameters. This is the place, where gradients get stored for parameters.
This function is the true objective, which wants to be minimized. This function is the true objective, which wants to be minimized.
Note that all parameters are already set and in place, so you just need Note that all parameters are already set and in place, so you just need
to return the gradient here. to return the gradient here.
For probabilistic models this is the gradient of the negative log_likelihood For probabilistic models this is the gradient of the negative log_likelihood
(including the MAP prior), so we return it here. If your model is not (including the MAP prior), so we return it here. If your model is not
probabilistic, just return your *negative* gradient here! probabilistic, just return your *negative* gradient here!
""" """
return -(self._log_likelihood_gradients() + self._log_prior_gradients()) return -(self._log_likelihood_gradients() + self._log_prior_gradients())
@ -227,13 +227,15 @@ class Model(Parameterized):
if optimizer is None: if optimizer is None:
optimizer = self.preferred_optimizer optimizer = self.preferred_optimizer
elif isinstance(optimizer, optimization.Optimizer):
opt = optimizer
else:
optimizer = optimization.get_optimizer(optimizer)
opt = optimizer(start, model=self, **kwargs)
if start == None: if start == None:
start = self.optimizer_array start = self.optimizer_array
optimizer = optimization.get_optimizer(optimizer)
opt = optimizer(start, model=self, **kwargs)
opt.run(f_fp=self._objective_grads, f=self._objective, fp=self._grads) opt.run(f_fp=self._objective_grads, f=self._objective, fp=self._grads)
self.optimization_runs.append(opt) self.optimization_runs.append(opt)