Simulating quantum many-body dynamics on classical computers is a challenging problem due to the exponential growth of the Hilbert space. Artificial neural networks have recently been introduced as a new tool to approximate quantum-many body states. We benchmark the variational power of the restricted Boltzmann machine quantum states and different shallow and deep neural autoregressive quantum states to simulate global quench dynamics of a non-integrable quantum Ising chain. We find that the number of parameters required to represent the quantum state at a given accuracy increases exponentially in time. The growth rate is only slightly affected by the network architecture over a wide range of different design choices: shallow and deep networks, small and large filter sizes, dilated and normal convolutions, with and without shortcut connections.
On the origin of neural scaling laws: from random graphs to natural language
Meta Superintelligence Labs, FAIR（Meta超智能实验室，FAIR）；Department of Physics, University of Maryland, College Park（大学物理系，马里兰大学College Park分校）；Joint Quantum Institute（联合量子研究所）
Universal Scaling Laws of Absorbing Phase Transitions in Artificial Deep Neural Networks
Institute for Physics of Intelligence, The University of Tokyo（智能物理研究所，东京大学）；AI Laboratory, Aisin Corporation（爱思特实验室，爱思特公司）；Department of Physics, The University of Tokyo（物理系，东京大学）；Institute for Solid State Physics, The University of Tokyo（固态物理研究所，东京大学）
