New comment by Devilstro in "A polynomial autoencoder beats PCA on transformer embeddings"

Devilstro — Fri, 08 May 2026 08:05:01 +0000

In the article, you mention this approach requires no search over hyper-parameter, because the method comprises a closed-form solution with "simple" linear algebra. I agree with this, but do you not in think need to tune the L2-regularization strength? That would for me be a hyper-parameter you would need to do a CV over (or similarly).

Hacker News: Devilstro

New comment by Devilstro in "A polynomial autoencoder beats PCA on transformer embeddings"