dfm / dfm/tinygp

The L1Distance is often numerically unstable

Open
#122 1 comment 0 reactions 1 assignee View on GitHub

@dfm is already working on this.

Since Oct 28, 2022.

enhancement
Dominant language
Python
Stars
349
Forks
35
Avg merge
2d 2h
Merged PRs (30d)
1

Description

Is this a bug? Should we change the default distance for the Matern kernels?

For example, the following:

import numpy as np
from tinygp import GaussianProcess, kernels

random = np.random.default_rng(48392)
X = random.uniform(-1, 1, (100, 2))
kernel = kernels.Matern32()
print(GaussianProcess(kernel, X, diag=0.01).solver.normalization())

returns NaN, but replacing the kernel with:

kernel = kernels.Matern32(distance=kernels.L2Distance())

works…

See also #115

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.