v0.0.11

What's Changed

• Update the example notebook by @rlouf in #85
• Updates to copyright years, cast policy, and pre-commit by @brandonwillard in #86

Full Changelog: v0.0.10...v0.0.11

v0.0.10

What's Changed

• Fix error in README example by @rlouf in #82
• Update ShapeFeature imports by @brandonwillard in #81

Full Changelog: v0.0.9...v0.0.10

v0.0.9

What's Changed

• Change use of "opt[imize]" to "rewrite" by @brandonwillard in #80

Full Changelog: v0.0.8...v0.0.9

v0.0.8

What's Changed

• Fix schedule length for small number of adaptation steps by @rlouf in #77

Full Changelog: v0.0.7...v0.0.8

v0.0.7

What's Changed

• Add environment.yml and update Python version in CI by @rlouf in #73
• Do not return window adaptation's final by @rlouf in #74
• Skip trajectory building if the first step diverges by @rlouf in #76

Full Changelog: v0.0.6...v0.0.7

v0.0.6

What's Changed

• Fix RaveledParamsMap dtypes by @rlouf in #61
• Code cleanup by @rlouf in #64
• Refactor the kernel and adaptation API by @rlouf in #66

Full Changelog: v0.0.5...v0.0.6

v0.0.5

What's Changed

• Make the HMC & NUTS kernels return scan updates by @rlouf in #56
• Fix test seeding by @brandonwillard in #57
• Implement window adaptation by @rlouf in #48
• Fix the computation of the trajectory weights by @rlouf in #58

Full Changelog: v0.0.4...v0.0.5

v0.0.4

What's Changed

• Return inner-Scan updates instead of setting default_updates by @brandonwillard in #55

Full Changelog: v0.0.3...v0.0.4

v0.0.3

What's Changed

• Add README by @rlouf in #25
• Build the NUTS kernel with a logprob function by @rlouf in #31
• Add dual averaging algorithm by @rlouf in #35
• Add Welford's online algorithm by @rlouf in #38
• Add function to create a new HMC (or NUTS) state by @rlouf in #29
• Add Stan window adaptation schedule by @rlouf in #43
• Implement step-size adaptation by @rlouf in #41
• Implement mass matrix adaptation by @rlouf in #44
• Fix NUTS by @rlouf in #45
• Raise exception on shape error in CI by @rlouf in #42
• Replace aet aliases with at. by @twiecki in #51
• Re-run the linear regression example by @rlouf in #52
• Do not return Scan updates from kernels by @rlouf in #53
• Acceptance probability in NUTS by @rlouf in #54

New Contributors

• @twiecki made their first contribution in #51

Full Changelog: v0.0.2...v0.0.3

v0.0.2

• Initial HMC and NUTS implementations