Provably Efficient Quantum Algorithms for Nonlinear Dynamics and Machine Learning
Institute for Pure & Applied Mathematics (IPAM) via YouTube
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a cutting-edge lecture on quantum algorithms for nonlinear dynamics and large-scale machine learning models. Delve into the groundbreaking research presented by Jin-Peng Liu from the University of California, Berkeley, at IPAM's Quantum Algorithms for Scientific Computation Workshop. Discover the first efficient quantum algorithm for nonlinear differential equations with strong dissipation, offering an exponential improvement over previous methods. Examine the established lower bound for weakly dissipative systems and the resulting classification of quantum complexity in simulating nonlinear dynamics. Learn about the innovative quantum algorithm for training classical sparse neural networks, including its application to ResNet with up to 103 million parameters on the Cifar-100 dataset. Gain insights into how fault-tolerant quantum computing can enhance the scalability and sustainability of state-of-the-art machine learning models.
Syllabus
Jin Peng Liu - Provably Efficient Quantum Algorithms for Nonlinear Dynamics and Machine Learning
Taught by
Institute for Pure & Applied Mathematics (IPAM)