Boolean satisfiability (SA T) is a fundamental problem in computer science.

Bayesian optimisation (BO) is a powerful framework for global optimisation of costly functions, using predictions from Gaussian process models (GPs).

In order to address this limitation, we propose a novel class of functions that can characterize the loss landscape of modern deep models without requiring extensive over-parametrization and can also include saddle points.

Large language models (LLMs) with billions of parameters demonstrate impressive performance.

Trained on vast corpora of human language, language models demonstrate emergent human-like reasoning abilities.