Hierarchical Search of Tree Tensor Networks for High-Dimensional Data

Abstract

Tensor network methods provide a scalable solution to represent high-dimensional data. However, their efficacy is often limited by static, expert-defined structures that fail to adapt to evolving data correlations. We address this limitation by formalizing the structural rounding problem for tree tensor networks and introducing a hierarchical search algorithm HIST, which automatically identifies optimized structures with index reshaping for input tree tensor networks. To navigate the combinatorial explosion of the structural search space, HIST integrates stochastic sub-network sampling with hierarchical refinement. This approach utilizes entropy-guided index clustering to reduce dimensionality and targeted reshaping to expose latent data correlations. Numerical experiments on analytical functions and real-world physics applications, including thermal radiation transport, neutron diffusion, and computational fluid dynamics, demonstrate that HIST exhibits empirical polynomial scaling with dimensionality relative to the sampling budget, bypassing the scalability barriers in prior work. HIST achieves compression ratios $2.5\times$ to $100\times$ higher than standard fixed formats such as Tensor Trains and Hierarchical Tuckers (peaking at $1000\times$). Furthermore, HIST discovers structures that generalize effectively: applying a structure optimized for one data instance to a related target data typically maintains compression performance within $10\%$ of the result obtained by performing structure search on that target data. These results highlight HIST as a robust, automated tool for adaptive data representation and high-dimensional simulation compression with tensor network methods.

References in corpus (17)

• Classical simulation of quantum many-body systems with a tree tensor network
• Density matrix renormalization group algorithms with a single center site
• Loop optimization for tensor network renormalization
• Efficient Tree Tensor Network States (TTNS) for Quantum Chemistry: Generalizations of the Density Matrix Renormalization Group Algorithm
• Minimal subspace rotation on the Stiefel manifold for stabilization and enhancement of projection-based reduced order models for the compressible Navier-Stokes equations
• Gauge fixing, canonical forms and optimal truncations in tensor networks with closed loops
• An Implicit Finite Volume Scheme to Solve the Time Dependent Radiation Transport Equation Based on Discrete Ordinates
• Tree tensor network state approach for solving hierarchical equations of motion
• Automatic structural optimization of tree tensor networks
• Hyper-optimized approximate contraction of tensor networks with arbitrary geometry
• Adaptive-weighted tree tensor networks for disordered quantum many-body systems
• Tree-based tensor formats
• The Three-Legged Tree Tensor Networks with SU(2)- and molecular point group symmetry
• A Finite Element Method for Angular Discretization of the Radiation Transport Equation on Spherical Geodesic Grids
• Tensor-network strong-disorder renormalization groups for random quantum spin systems in two dimensions
• Tensor rank reduction via coordinate flows
• Fermionic tensor network contraction for arbitrary geometries