\ud83d\uddd3\ufe0f07\/10\/2025<\/p>\n\n\n\n
Speaker:<\/strong> Hsin-Yuan Huang (Robert)<\/p>\n\n\n\n Title: <\/strong>Generative quantum advantage for classical and quantum problems<\/p>\n\n\n\n Abstract:<\/strong> Recent breakthroughs in generative machine learning, powered by massive computational resources, have demonstrated unprecedented human-like capabilities. While beyond-classical quantum experiments have generated samples from classically intractable distributions, their complexity has thwarted all efforts in efficient learning.<\/p>\n\n\n\n This challenge has hindered demonstrations of generative quantum advantage: the ability for quantum computers to both learn and generate desired outputs substantially better than classical computers. We resolve this rigorously by introducing generative quantum models that are hard to simulate classically, provably efficiently trainable in every step, exhibit no barren plateaus or proliferating local minima, and generate distributions beyond classical reach with rigorous guarantees.<\/p>\n\n\n\n Using a 68-qubit superconducting quantum processor, we apply these models to two scenarios: learning classically intractable probability distributions and learning quantum circuits for accelerated physical simulation. Our results demonstrate that both learning and sampling are efficient in the current beyond-classical regime, opening new possibilities for quantum-enhanced generative models with provable advantage.<\/p>\n\n\n\n