Skip to content

Conversation

@avehtari
Copy link
Member

When using approximate inference algorithm fit objects as init there could be some errors that this PR fixes

  • Issue: lp__ or lp_approx__ may contain NaN. NA, or Inf. Fix: replace non-finite lw with -Inf
  • Issue: pareto_smooth() was estimating r_eff, but for independent draws from approximate normals r_eff=1 should be used: Fix: add argument r_eff=1 to pareto_smooth() call

@avehtari avehtari requested a review from andrjohns May 24, 2024 08:39
Copy link
Collaborator

@andrjohns andrjohns left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks! Looks good, just one question

@andrjohns andrjohns merged commit 1679aa7 into master May 24, 2024
@andrjohns andrjohns deleted the process_init_approx_fix branch May 24, 2024 11:08
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants