38 commits

Author	SHA1	Message	Date
Moreno	11aa6ea27b	Serialization: Add docstrings	2018-06-07 09:52:13 +01:00
Moreno	e572bfb746	Basic framework for serializing GPy models	2017-09-11 12:18:01 +01:00
Moreno	0c248e7520	Changes in EP/EPDTC to fix numerical issues and increase the flexibility of the inference. ... Changes to avoid numerical issues and improve the performance: - Keep value of the EP parameters between calls - Enforce positivity of tau_tilde - Stable computation of the EP moments for the Bernoulli likelihood - Compute marginal in the GP model without directly inverting tau_tilde Changes to improve the flexibility: - Add parameter for maximum number of iterations - Distinguish between alternated/nested mode - Distinguish between sequential/parallel updates in EP	2017-03-22 13:40:06 +00:00
Alan Saul	e7c8da2cdf	Added Y_metadata to moments_match_ep, and removed log-concave student-t test, and added EP test for bernoulli	2015-10-22 16:20:16 +01:00
Alan Saul	5b4abf4c34	Fixing bernoulli likelihood for Laplace, fixing Zep for EP, and starting working on quadrature limits	2015-10-19 19:29:57 +01:00
Max Zwiessele	8132084de6	[ep] now calling exact inference instead of copying code	2015-09-11 15:47:07 +01:00
Max Zwiessele	1d354f5cce	[classification] sparse gp classification and dtc update	2015-09-11 15:08:30 +01:00
James Hensman	60b5f071b4	sqrt(pi) term fix in Bernoulli	2015-08-18 17:11:54 +01:00
James Hensman	9780fb48de	fixing qualtile code for some likelhoods	2015-08-13 12:07:01 +01:00
James Hensman	ea787fd376	manual merging	2015-04-09 15:46:40 +01:00
James Hensman	1e30ffd730	speed ups for normal cdf	2015-04-09 15:42:02 +01:00
Mike Croucher	e82b5fe773	Resolve merge conflicts	2015-04-01 11:44:20 +01:00
James Hensman	534e0df606	some tests for the svgp, and some changes to the likelihoods	2015-03-24 14:11:50 +00:00
Mike Croucher	29da6ff065	Merge remote-tracking branch 'upstream/devel' into devel	2015-02-26 08:25:51 +00:00
Mike Croucher	2ca24a88f5	More relative import fixes for Python 3 compatibility	2015-02-26 07:14:40 +00:00
James Hensman	393b9e94ba	added more stable expectations for Bernoulli	2015-02-10 16:15:37 +00:00
Alan Saul	935f2016db	Fixed quadrature for bernoulli likelihood, started adding Gaussian likelihood derivatives for quadrature	2014-12-19 17:53:32 +00:00
James Hensman	f8fa672ea1	more cooooopyrighting	2014-11-21 11:59:02 +00:00
James Hensman	d9022c8cee	stabilization of the Bernouolli	2014-11-13 11:18:25 +00:00
James Hensman	d26beb215a	numerical stability in variational expectations	2014-10-16 17:32:37 +01:00
James Hensman	30343f5e53	more variational quadtrature code	2014-10-16 15:41:01 +01:00
James Hensman	84c87f7886	beginning of adding variational GH quadrature to the likelihood class	2014-10-16 12:14:56 +01:00
Ricardo	3d76664af0	EP is back.	2014-05-15 16:36:03 +01:00
Neil Lawrence	6f86b9b0fa	Update of symbolic likelihoods.	2014-03-31 09:18:31 +01:00
James Hensman	601175de2d	very weird merge conflict, including in files that I did not change	2014-03-18 16:46:37 +00:00
James Hensman	da2cceba87	plotting now seems to work for Bernouilli	2014-03-14 12:19:25 +00:00
James Hensman	77d08a7d6f	fixes to EP	2014-03-14 11:47:23 +00:00
James Hensman	b7508ce12b	various fixes in likelihoods, esp studentT and plotting	2014-03-13 15:35:54 +00:00
James Hensman	2876e5a07a	work on likeluhoods and likelihoods tests	2014-02-27 15:37:31 +00:00
James Hensman	66577a8fb0	more bugfixin	2014-02-24 14:58:28 +00:00
James Hensman	d7f217d8af	bugfixin in bernioulli	2014-02-24 14:57:23 +00:00
Alan Saul	46ce76dee8	Fixed bernoulli likelihood divide by 0 and log of 0	2014-02-12 16:48:57 +00:00
James Hensman	80629e00b6	fiddling with plotting	2014-02-05 17:12:52 +00:00
James Hensman	63ab143e7c	some tifying in the models classes	2013-12-12 14:18:18 +00:00
James Hensman	cd3bcee11c	some minor edit to Bernoulli	2013-12-12 02:27:20 -08:00
James Hensman	f1a08fbfdb	mostly docstring noodling	2013-12-11 15:42:25 -08:00
James Hensman	5ec64d2279	more massive and destructive changes everywhere	2013-12-05 15:09:31 -05:00
James Hensman	83a495645d	some more messing with the likelihood directory	2013-12-04 11:32:12 +00:00