Repository navigation
Add the generalized extreme value distribution, and port test_negative_binomial to math_unit_test - #1573
Merged
Conversation
NAThompson
force-pushed
the
gev-and-negbin-port
branch
5 times, most recently
from
October 13, 2026 03:44
6fceaee to
7085ea8
Compare
…e_binomial to math_unit_test Location, scale and shape as on Wikipedia, with log1p/expm1 forms continuous through the Gumbel case and moments summed from the zeta series of lgamma where their Gamma combinations cancel. The negative binomial quantile checks now scale with the quantile's condition number, which reached 548 near zero and failed windows_gcc. The nanobind distributions get their parameters as properties and a repr that rebuilds them. SYCL tests build with -fp-model=precise, dropping three fast-math workarounds. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
NAThompson
force-pushed
the
gev-and-negbin-port
branch
from
October 13, 2026 06:15
7085ea8 to
dd7e6d0
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Location, scale and shape as on Wikipedia, with log1p/expm1 forms continuous through the Gumbel case and moments summed from the zeta series of lgamma where their Gamma combinations cancel. The negative binomial quantile checks now scale with the quantile's condition number, which reached 548 near zero and failed windows_gcc. The nanobind distributions get their parameters as properties and a repr that rebuilds them. SYCL tests build with -fp-model=precise, dropping three fast-math workarounds.
Co-Authored-By: Claude Opus 5.5 noreply@anthropic.com
Requested by @WarrenWeckesser on #303. Accuracy against closed forms in 50 digits (orange: the error a half-ulp change in the argument causes):
2D: the error over the condition number's envelope, |ulps|/max(1/2, cond/2), against the closed forms in 50 digits; small xi is sampled down to 1e-12 on a log axis:
🤖 Generated with Claude Code