A 256 256 image size is used so that the ViT encoder generates 256 tokens. We follow the process used in Tsimpoukelli et al. Randomly sampled image from ImageNet. Randomly sampled image from ImageNet.

Augmenting tactic-based interactive theorem provers with neural guidance has been the focus of increased attention in recent years [1, 2, 3, 4, 5]. The dominant approach uses imitation learning on corpora of formalized mathematics. However, despite recent efforts involving self-supervised pre-training [5] or data-augmentation [6], this approach is limited by the conspicuous scarcity of human-producedtrainingdata.

A wide range of applications from Auto-ML [15] to chemistry [6] and drug design [3] require optimizing ablack-boxobjectivefunction (i.e.,itsclosed-form expression, gradient, andconvexity are unknown) through observing noisy function evaluations.