Acknowledgements

We thank Pavel Izmailov, Polina Kirichenko, and Wesley Maddox for helpful discussions. This research is supported by NSF CAREER IIS-2145492, NSF I-DISRE 193471, NIH R01DA048764-01A1, NSF IIS-1910266, NSF 1922658 NRT-HDR: FUTURE Foundations, Translation, and Responsibility for Data Science, Meta Core Data Science, Google AI Research, BigHat Biosciences, Capital One, and an Amazon Research Award. An image is worth 16x16 words: Transformers for image recognition at scale. The pascal visual object classes (voc) challenge. Bayesian neural network priors revisited.