Engineering quantum matter with generative machine learning

Quantum matter presents a rich landscape of emergent phenomena and exotic properties that are rare in natural compounds. This includes many-body systems such as topological insulators and unconventional superconductors. Understanding and characterizing these systems presents significant challenges due to their complexity and exotic behavior. In this dissertation, we explore the intersection of condensed matter theory, quantum matter, and artificial intelligence (AI). We demonstrate how machine learning (ML) can be used as a powerful tool for untangling complex problems in quantum many-body physics and go beyond conventional methods. Generative ML methods allow us to design complex quantum materials efficiently, optimize experimental parameters, uncover hidden correlations of quantum many-body systems, and bring together experiments and theoretical models. With this thesis, we aim to provide a complementary strategy to design exotic quantum phenomena, making a step towards future technological advancements in correlated quantum materials, materials science, and quantum computing.