lanl / PRISM
13%
master: 11%

LAST BUILD BRANCH: diagonal_variational_cov
DEFAULT BRANCH: master
Repo Added
Token cSmD9cuxSr9DEUEHA7CpfEfz7BTjei9Y3 regen
Build 75 Last
Files 12
Badge
Embed ▾
README BADGES
x

If you need to use a raster PNG badge, change the '.svg' to '.png' in the link

Markdown

Textile

RDoc

HTML

Rst

LAST BUILD ON BRANCH diagonal_variational_cov
branch: SELECT
CHANGE BRANCH
x
Sync Branches

coverage: 12.99%. Remained the same
6870864091

push

github

web-flow 
Update Project.toml

Telling HSVGP on this branch that it is compatible with relevant MPI.jl versions

106 of 816 relevant lines covered (12.99%)

11568.84 hits per line

Relevant lines Covered
816 RELEVANT LINES 106 COVERED LINES
11568.84 HITS PER LINE
Source Files on master

Recent builds

Builds Branch Commit Type Ran Committer Via Coverage
6870864091 diagonal_variational_cov Update Project.toml Telling HSVGP on this branch that it is compatible with relevant MPI.jl versions push web-flow github
12.99
3245657378 stratified_psvgp Implemented a version of PSVGP with proper stratified sampling to compare to version to be published. The full stratified sampling approach hurts the scaling because of the great increase in communication. push Mike Grosskopf github pending completion  
3200821570 master Also go to sampling without replacement unless the batch size > local num obs push Mike Grosskopf github pending completion  
3199741941 master Substantial changes to PSVGP to handle unbalanced partitions. Some other touchups in the process. push Mike Grosskopf github pending completion  
3102308235 master Important fix to PSVGP code that Kelin really needs for what he is doing. push Mike Grosskopf github pending completion  
2755413324 master Adding the nugget to S and correcting issue with frac_local at corners push Mike Grosskopf github pending completion  
2755156617 master Update prediction.jl push GitHub github pending completion  
2714784026 master Making the SVGP_data structures mutable so that one can transfer a model fit on some inputs and retrain it on new inputs. Previously the training data for a GP object was fixed for simple SVGPs. It was variable for the distributed GPs though. push Michael Grosskopf github pending completion  
2707980934 master Adding an attempt at the capability to do streaming GPs by using the previous GP as the prior for the new one. This currently is not working particularly well in a simple test but a version is implemented here. push Michael Grosskopf github pending completion  
2678169990 master Dont know how this worked right in the past or if it didnt quite, but its fixed now push Mike Grosskopf github pending completion  
See All Builds (75)

Badge your Repo: PRISM

We detected this repo isn’t badged! Grab the embed code to the right, add it to your repo to show off your code coverage, and when the badge is live hit the refresh button to remove this message.
Embed ▾
README BADGES
x

If you need to use a raster PNG badge, change the '.svg' to '.png' in the link

Markdown

Textile

RDoc

HTML

Rst

Refresh