SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective

arXiv:2305.14912v5 Announce Type: replace
Abstract: Tensor network (TN) representation is a powerful technique for computer vision and machine learning. TN structure search (TN-SS) aims to search for a customized structure to achieve a compact representation, which is a challenging NP-hard problem. Recent "sampling-evaluation"-based methods require sampling an extensive collection of structures and evaluating them one by one, resulting in prohibitively high computational costs. To address this issue, we propose a novel TN paradigm, named SVD-inspired TN decomposition (SVDinsTN), which allows …

abstract arxiv compact computer computer vision cs.lg evaluation machine machine learning modeling network np-hard paradigm perspective representation sampling search tensor type vision