all AI news
Meta-Learning a Real-Time Tabular AutoML Method For Small Data. (arXiv:2207.01848v1 [cs.LG])
stat.ML updates on arXiv.org arxiv.org
We present TabPFN, an AutoML method that is competitive with the state of the
art on small tabular datasets while being over 1,000$\times$ faster. Our method
is very simple: it is fully entailed in the weights of a single neural network,
and a single forward pass directly yields predictions for a new dataset. Our
AutoML method is meta-learned using the Transformer-based Prior-Data Fitted
Network (PFN) architecture and approximates Bayesian inference with a prior
that is based on assumptions of simplicity …
arxiv automl data learning lg meta meta-learning real-time small small data tabular time