Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Revival of MCMCTempering.jl #158

Merged
merged 17 commits into from
Sep 30, 2024
Merged

Revival of MCMCTempering.jl #158

merged 17 commits into from
Sep 30, 2024

Commits on Sep 23, 2024

  1. Bump breaking releases for project deps

    @torfjelde
    torfjelde committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    2d2278e View commit details
    Browse the repository at this point in the history

  2. Updated init_params kwarg which is now initial_params after Abstr… 

    …[email protected]
    @torfjelde
    torfjelde committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    376ef60 View commit details
    Browse the repository at this point in the history

  3. Updated more init_params to initial_params

    @torfjelde
    torfjelde committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    efbe913 View commit details
    Browse the repository at this point in the history

  4. Fixed incorrect references to stuff in AdvancedMH.jl and AdvancedHMC.jl

    @torfjelde
    torfjelde committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    11c7851 View commit details
    Browse the repository at this point in the history

Commits on Sep 25, 2024

  1. Added fix for AdvancedHMC.jl needing n_adapts as kwarg

    @torfjelde
    torfjelde committed Sep 25, 2024
    Configuration menu
    Copy the full SHA
    6271d20 View commit details
    Browse the repository at this point in the history

  2. Replaced DynamicPPL.jl model since the inverse gamma conjugate model 

    has very high variance fwhen working with so few observations + using
initial parameters in constrained space rather than unconstrained
space since this has been addressed in `Turing.externalsampler`
    @torfjelde
    torfjelde committed Sep 25, 2024
    Configuration menu
    Copy the full SHA
    7b79743 View commit details
    Browse the repository at this point in the history

  3. Relaxed significance in atol_for_chain

    @torfjelde
    torfjelde committed Sep 25, 2024
    Configuration menu
    Copy the full SHA
    5181f80 View commit details
    Browse the repository at this point in the history

  4. Relaxed on test slightly

    @torfjelde
    torfjelde committed Sep 25, 2024
    Configuration menu
    Copy the full SHA
    1e0384d View commit details
    Browse the repository at this point in the history

  5. Updated docs

    @torfjelde
    torfjelde committed Sep 25, 2024
    Configuration menu
    Copy the full SHA
    dcf589b View commit details
    Browse the repository at this point in the history

Commits on Sep 26, 2024

  1. Use slightly better initialization for Turing.jl tests

    @torfjelde
    torfjelde committed Sep 26, 2024
    Configuration menu
    Copy the full SHA
    722ac8f View commit details
    Browse the repository at this point in the history

  2. Added some debugging statement for tests

    @torfjelde
    torfjelde committed Sep 26, 2024
    Configuration menu
    Copy the full SHA
    4088a9f View commit details
    Browse the repository at this point in the history

  3. Use median instead of mean in a test to lower the variance of the 

    estimate a bit
    @torfjelde
    torfjelde committed Sep 26, 2024
    Configuration menu
    Copy the full SHA
    03e84b3 View commit details
    Browse the repository at this point in the history

  4. Further relaxation of tests

    @torfjelde
    torfjelde committed Sep 26, 2024
    Configuration menu
    Copy the full SHA
    96df9a6 View commit details
    Browse the repository at this point in the history

  5. Narrowed signficiance in atol_for_chain but added min_atol kwarg 

    to alllow us to specify a minimum atol that we're happy with
    @torfjelde
    torfjelde committed Sep 26, 2024
    Configuration menu
    Copy the full SHA
    9730b1a View commit details
    Browse the repository at this point in the history

Commits on Sep 30, 2024

  1. Use elementwise comparison for a mean rather than vector-based approx

    @torfjelde
    torfjelde committed Sep 30, 2024
    Configuration menu
    Copy the full SHA
    2a8ab0e View commit details
    Browse the repository at this point in the history

  2. Made the test suite a bit more consistent by using explicit RNGs here 

    and there
    @torfjelde
    torfjelde committed Sep 30, 2024
    Configuration menu
    Copy the full SHA
    a4ec00b View commit details
    Browse the repository at this point in the history

  3. Forgot an RNG in one sample

    @torfjelde
    torfjelde committed Sep 30, 2024
    Configuration menu
    Copy the full SHA
    8341262 View commit details
    Browse the repository at this point in the history