A recent paper published in Nature caught my eye, Accurate predictions on small data with a tabular foundation model by Hollmann et al.,
Here we present the Tabular Prior-data Fitted Network (TabPFN), a tabular foundation model that outperforms all previous methods on datasets with up to 10,000 samples by a wide margin, using substantially less training time.
I thought it might be interesting to see how this performs on Apple Silicon, you can read the post here