Tensor-networks for High-order Polynomial Approximation: A Many-body Physics Perspective
This work connects quantum information and functional approximation, offering a novel perspective for researchers in machine learning and physics, though it appears incremental as it applies existing tensor-network methods to a new context.
The paper tackled high-order polynomial approximation by analyzing it from a many-body physics perspective, showing that entanglement entropy captures model capacity and task complexity, with tensor-network models demonstrating promising advantages in a nonlinear dynamics modeling problem.
We analyze the problem of high-order polynomial approximation from a many-body physics perspective, and demonstrate the descriptive power of entanglement entropy in capturing model capacity and task complexity. Instantiated with a high-order nonlinear dynamics modeling problem, tensor-network models are investigated and exhibit promising modeling advantages. This novel perspective establish a connection between quantum information and functional approximation, which worth further exploration in future research.