apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-04-29 06:46:22 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
5251 commits 38 branches 52 tags 68 MiB
Commit graph

5251 commits

This branch
This branch
All branches
Author SHA1 Message Date
Akash Kumar Dhaka
38597b1ede removing pods dependency and a few print commands 2017-08-10 11:14:40 +03:00
Akash Kumar Dhaka
69a81acff9 bug fix to prevent infinite loop because of incorrect stopping condition 2017-08-10 11:14:40 +03:00
Akash Kumar Dhaka
54f530a22b adding some test cases for EP.. more work needs to be done, these are some high level test cases .. 2017-08-10 11:14:40 +03:00
Moreno
255d97a917 Refactor EP and EPDTC 2017-08-10 11:14:40 +03:00
esiivola
7c4e2f21f8 Added initial version of the refactored EP 2017-08-10 11:14:40 +03:00
esiivola
0d06dc3b4e Added initial version of the refactored EP 2017-08-10 11:14:40 +03:00
esiivola
dfc5bd42dc Added initial version of the refactored EP 2017-08-10 11:14:40 +03:00
mzwiessele
e849a4c62d fix: pkg: CHANGELOG 2017-08-10 11:14:40 +03:00
mzwiessele
b143e92b5c Bump version: 1.6.1 → 1.6.2 2017-08-10 11:14:40 +03:00
mzwiessele
000d832830 fix: updated keywords 2017-08-10 11:14:40 +03:00
Alex Feldstein
6f738bd2b4 fix in sparse_gp_mpi optimizer 2017-08-10 11:14:40 +03:00
Alex Feldstein
ef924eba6c fix for parallel optimization 2017-08-10 11:14:40 +03:00
Moreno
63751de912 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
 2017-06-01 11:59:04 +03:00
Max Zwiessele
113f84d6a7 cython in linalg 
did set cython to working if linalg_cython was importable.
 2017-06-01 11:59:04 +03:00
mzwiessele
8c72eb2932 chg: pkg: CHANGELOG update 2017-06-01 11:59:04 +03:00
mzwiessele
335ecec584 Bump version: 1.6.0 → 1.6.1 2017-06-01 11:59:04 +03:00
mzwiessele
0ee2910391 fix: beiwang will add GMM in full 2017-06-01 11:59:04 +03:00
mzwiessele
cc93fe54af chg: pkg: CHANGELOG update 2017-06-01 11:59:04 +03:00
mzwiessele
7b58495dc7 Bump version: 1.5.9 → 1.6.0 2017-06-01 11:59:04 +03:00
mzwiessele
011e3d6439 fix: kernel tests and variational tests 2017-06-01 11:59:04 +03:00
mzwiessele
703a136c8c fix: plotting tests for new matplotlib 2017-06-01 11:59:04 +03:00
mzwiessele
970bd5399b fix: model tests numpy integer error 2017-06-01 11:59:04 +03:00
mzwiessele
b8aabb97f8 fix: replot with new matplotlib 2017-06-01 11:59:04 +03:00
mzwiessele
1b9b1a95a6 fix: offline plotting workaround with squeezing arrays 2017-06-01 11:59:04 +03:00
mzwiessele
96cc0838eb fix: Fixed numpy 1.12 indexing and shape preservation 2017-06-01 11:59:04 +03:00
Alex Feldstein
a7a2e53f6d provide two classes for plotly plots to remove global variable 2017-06-01 11:59:04 +03:00
mzwiessele
a207d09d2b fix: pkg: changelog 2017-06-01 11:59:04 +03:00
mzwiessele
450717c5c8 Bump version: 1.5.8 → 1.5.9 2017-06-01 11:59:04 +03:00
mzwiessele
9cacf46c18 chg: pkg: CHENGELOG update 2017-06-01 11:59:04 +03:00
mzwiessele
756b618ef4 Bump version: 1.5.7 → 1.5.8 2017-06-01 11:59:04 +03:00
mzwiessele
9eee68e831 fix: pkg: dim reduction simulation with different functions 2017-06-01 11:59:04 +03:00
Alex Feldstein
66bd0b6583 add offline plotting for plotly 2017-06-01 11:59:04 +03:00
Zhenwen Dai
e74a31c482 Update ss_gplvm.py 
resolve the future warning: FutureWarning:comparison to `None` will result in an elementwise object comparison in the future.
 2017-01-29 11:38:13 +00:00
Max Zwiessele
fce0e4258b Merge pull request #472 from SheffieldML/predictive_gradients 
fix: predictive_gradients for new posterior class
 2017-01-10 15:43:56 +00:00
mzwiessele
6fc0cc630c fix: predictive_gradients for new posterior class 2017-01-10 14:38:09 +00:00
Max Zwiessele
f36a394766 Merge pull request #470 from SheffieldML/plotting_fix 
Plotting fix
 2017-01-10 13:48:28 +00:00
mzwiessele
b17b92043c chg: pkg: CHANGELOG update 2017-01-10 12:53:34 +00:00
mzwiessele
3608cff438 Bump version: 1.5.6 → 1.5.7 2017-01-09 11:05:20 +00:00
mzwiessele
b6d2cf4406 fix: removed additional dict line 2017-01-09 11:01:30 +00:00
mzwiessele
fe3bad7200 fix: plotting also allows 3D (capitals) 2017-01-09 10:59:51 +00:00
Safrone
14046705cf fix: fallback for when no environment variables are set (#467) 
* fix: dev: add or in home directory getting

adds another or when getting the home directory with os.getenv() so that if neither $HOME nor $USERPROFILE environment variable is set, os.path.join() will not fail by getting a None and the config will revert to the default configuration file.

* fix: remove extra statement
 2017-01-09 09:50:29 +00:00
Teo de Campos
a2f67febb4 Changed the order of the operations, ensuring that the covariance matrix is symmetric despite numerical precision issues. 
Suggested by Alan.
 2016-12-06 11:01:45 -02:00
beiwang
b1935292d9 Delete gmm_bayesian_gplvm.py 2016-11-11 19:54:57 +00:00
beiwang
567601344c gmm_creation 2016-11-11 19:18:39 +00:00
beiwang
6aab528af2 gmm_creation 2016-11-11 18:12:14 +00:00
mzwiessele
daa28f5e60 fix: pkg: changelogrc and changelog update 2016-11-07 10:54:04 +00:00
mzwiessele
5d480bfc68 fix: pkg: gitchangelog rc had missing line 2016-11-07 10:52:23 +00:00
mzwiessele
977d336148 Bump version: 1.5.5 → 1.5.6 2016-11-07 10:50:43 +00:00
Max Zwiessele
975b561d96 Merge pull request #448 from thangbui/devel 
Added pep.py -- Sparse Gaussian processes using Power Expectation Propagation
 2016-11-07 10:48:49 +00:00
Thang Bui
7b384ae258 renamed pep test scripts 2016-11-07 09:54:50 +00:00