Posted on June 25, 2023 by Samuel Müller
Can we replace the GP in BO with in-context learning? Absolutely. We achieve strong real-world performance on a variety of benchmarks with a PFN that uses only in-context learning to provide training values. This is what we found out in our ICML ‘23 paper PFNs4BO: In-Context Learning for Bayesian Optimization. Our models are trained only […]
Posted on October 11, 2022 by Samuel Müller, Katharina Eggensperger, Frank Hutter
A radically new approach to tabular classification: we introduce TabPFN, a new tabular data classification method that takes < 1 second & yields SOTA performance (competitive with the best AutoML pipelines in an hour). So far, it is limited in scale, though: it can only tackle problems up to 1000 training examples, 100 features and […]
Posted on August 18, 2021 by Samuel Müller
Strong image classification models need augmentations. That is consensus in the community for a few years now. Some augmentation choices became standard over the time for some datasets, but the question what augmentations strategy is optimal for a given dataset remained. This opened the opportunity of doing hyper-parameter optimization (HPO) to find optimal augmentation choices. […]
