# Kryptonite-N: Machine Learning Strikes Back

arXiv: https://arxiv.org/abs/2412.20588 · HTML: https://mlsanity.com/paper/2412.20588/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2024.

## Abstract (arXiv)

Quinn et al propose challenge datasets in their work called ``Kryptonite-N". These datasets aim to counter the universal function approximation argument of machine learning, breaking the notation that machine learning can ``approximate any continuous function" citeoriginalpaper. Our work refutes this claim and shows that universal function approximations can be applied successfully; the Kryptonite datasets are constructed predictably, allowing logistic regression with sufficient polynomial expansion and L1 regularization to solve for any dimension N.