search

mschauer / ZigZagBoomerang.jl

Sleek implementations of the ZigZag, Boomerang and other assorted piecewise deterministic Markov processes for Markov Chain Monte Carlo including Sticky PDMPs for variable selection
MIT License
101 stars 7 forks source link

Mass matrix #88

Closed mschauer closed 3 years ago

mschauer commented 3 years ago

Replaces #36

codecov-commenter commented 3 years ago

Codecov Report

Merging #88 (c2c7e96) into master (8239914) will decrease coverage by 0.15%. The diff coverage is 84.37%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master      #88      +/-   ##
==========================================
- Coverage   63.68%   63.52%   -0.16%     
==========================================
  Files          22       22              
  Lines        1407     1431      +24     
==========================================
+ Hits          896      909      +13     
- Misses        511      522      +11
Impacted Files Coverage Δ
src/not_fact_samplers.jl 78.16% <40.00%> (+0.77%) :arrow_up:
src/staticarrays.jl 62.50% <75.00%> (-37.50%) :arrow_down:
src/dynamics.jl 88.37% <100.00%> (-11.63%) :arrow_down:
src/types.jl 81.25% <100.00%> (ø)

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 8239914...c2c7e96. Read the comment docs.

mschauer commented 3 years ago

@andreabertazzi Maybe interesting for you (see "files changed" for an overview of the changes). I think my L is inv(M)' of your M.

I added support for mass matrices for Boomerang and Bouncy as a start, but not yet adaptive choice of them. The dynamics of the Boomerang are not affected by the mass-matrix here. That is something to check because I think you did it differently.