search

MilesCranmer / PySR

High-Performance Symbolic Regression in Python and Julia
https://astroautomata.com/PySR
Apache License 2.0
2.33k stars 211 forks source link

[Feature]: Measurement uncertainty #335

Open MilesCranmer opened 1 year ago

MilesCranmer commented 1 year ago

Feature Request

Should use Measurements.jl on the Julia side, and allow uncertainties array as input.

Loss function maybe could be Gaussian-Gaussian likelihood? Or KL divergence?

MilesCranmer commented 1 year ago

This is trickier than I thought, for the reason that the tree constants should be a different type than the data…