An MLP hits a real sample-complexity wall learning sparse parities, with a Fourier-basis progress measure that sees it coming before the loss does
-
Updated
Jul 10, 2026 - Python
An MLP hits a real sample-complexity wall learning sparse parities, with a Fourier-basis progress measure that sees it coming before the loss does
In this project we implement an algorithm provided in the paper "On the Learnability of Shuffle Ideals" which discusses the ability to PAC learn such shuffle ideals in a practical time complexity utilizing statistical queries.
Add a description, image, and links to the statistical-query topic page so that developers can more easily learn about it.
To associate your repository with the statistical-query topic, visit your repo's landing page and select "manage topics."