apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-04 01:02:39 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Updated other likelihoods to give back logpdf and gradients for each link_f rather than summing on the inside

Browse source
This commit is contained in:
Alan Saul 2015-03-09 10:27:21 +00:00
parent 48821a6b73
commit 233c5ee8b4
7 changed files with 22 additions and 42 deletions
Download patch file Download diff file Expand all files Collapse all files

6
GPy/likelihoods/exponential.py
View file

@ -57,9 +57,8 @@ class Exponential(Likelihood):
:rtype: float
"""
assert np.atleast_1d(link_f).shape == np.atleast_1d(y).shape
log_objective = np.log(link_f) - y*link_f
return np.sum(log_objective)
return log_objective
def dlogpdf_dlink(self, link_f, y, Y_metadata=None):
"""
@ -77,7 +76,6 @@ class Exponential(Likelihood):
:rtype: Nx1 array
"""
assert np.atleast_1d(link_f).shape == np.atleast_1d(y).shape
grad = 1./link_f - y
#grad = y/(link_f**2) - 1./link_f
return grad
@ -103,7 +101,6 @@ class Exponential(Likelihood):
Will return diagonal of hessian, since every where else it is 0, as the likelihood factorizes over cases
(the distribution for y_i depends only on link(f_i) not on link(f_(j!=i))
"""
assert np.atleast_1d(link_f).shape == np.atleast_1d(y).shape
hess = -1./(link_f**2)
#hess = -2*y/(link_f**3) + 1/(link_f**2)
return hess
@ -123,7 +120,6 @@ class Exponential(Likelihood):
:returns: third derivative of likelihood evaluated at points f
:rtype: Nx1 array
"""
assert np.atleast_1d(link_f).shape == np.atleast_1d(y).shape
d3lik_dlink3 = 2./(link_f**3)
#d3lik_dlink3 = 6*y/(link_f**4) - 2./(link_f**3)
return d3lik_dlink3