AI RESEARCH
Efficient Generative Modeling with Unitary Matrix Product States Using Riemannian Optimization
arXiv CS.LG
•
ArXi:2603.12026v1 Announce Type: new Tensor networks, which are originally developed for characterizing complex quantum many-body systems, have recently emerged as a powerful framework for capturing high-dimensional probability distributions with strong physical interpretability. This paper systematically studies matrix product states (MPS) for generative modeling and shows that unitary MPS, which is a tensor-network architecture that is both simple and expressive, offers clear benefits for unsupervised learning by reducing ambiguity in parameter updates and improving efficiency.