Machine learning models will often fail when deployed in an environment with a data distribution that is different than the training distribution.

Ontheonehand, thediversedata processing steps lead tothelack oflarge-scale7 benchmarks and therefore decelerate iterative methodology improvement on a8 single problem.

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.

One leading algorithmic paradigm on NISQ computers is theVariational Quantum Algorithm (VQA) with a few prominent examples like the Variational Quantum Eignensolver (VQE) [50], quantum approximate optimization algorithm (QAOA) [20], and more in [4]. Quantum machine learning isafast-developing emerging field (e.g., see the survey [5]) where variational quantum algorithms (VQAs) (e.g., see thesurvey[4]areoneofthemost promising candidates forNISQ applications.