Riemannian Optimization on Tree Tensor Networks with Application in Machine Learning
By: Marius Willner, Marco Trenti, Dirk Lebiedz
Potential Business Impact:
Makes computer learning faster and smarter.
Tree tensor networks (TTNs) are widely used in low-rank approximation and quantum many-body simulation. In this work, we present a formal analysis of the differential geometry underlying TTNs. Building on this foundation, we develop efficient first- and second-order optimization algorithms that exploit the intrinsic quotient structure of TTNs. Additionally, we devise a backpropagation algorithm for training TTNs in a kernel learning setting. We validate our methods through numerical experiments on a representative machine learning task.
Similar Papers
Derivatives of tree tensor networks and its applications in Runge--Kutta methods
Numerical Analysis
Finds better ways to solve math problems.
Regularized second-order optimization of tensor-network Born machines
Machine Learning (CS)
Teaches computers to learn patterns faster.
Deep Tree Tensor Networks for Image Recognition
CV and Pattern Recognition
Helps computers see more details in pictures.