Kryptonite-N: Machine Learning Strikes Back
This work addresses a foundational theoretical problem in machine learning by refuting claims that challenge universal function approximation, though it appears incremental as it applies an existing method to new data.
The authors tackled the challenge posed by the Kryptonite-N datasets, which were designed to counter the universal function approximation argument in machine learning, and demonstrated that logistic regression with polynomial expansion and L1 regularization can successfully solve these datasets for any dimension N.
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" \cite{original_paper}. 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.