Twirled Perfect Tensor Networks: Computationally covariant holographic tensor networks

• URL: http://arxiv.org/abs/2605.23670v1
• Date: Fri, 22 May 2026 14:18:32 GMT
• Title: Twirled Perfect Tensor Networks: Computationally covariant holographic tensor networks
• Abstract summary: We define a class of tensor networks motivated by the Python's Lunch Conjecture (PLC)<n>We show that the PLC makes implicit assumptions about the fine structure of the relevant tensor networks modeling gravity that render them non-generic.<n>We propose another class of tensor networks built from what we call "twirled perfect tensors"
• Score: 0.17592522344393483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We define a novel class of tensor networks motivated by the Python's Lunch Conjecture (PLC) in local tensor network models of the black hole interior. We start from the observation that, for extended black brane states with short-range correlations, the PLC predicts a complexity that is smaller than the upper bound for generic short-range correlated states. We argue that the PLC makes implicit assumptions about the fine structure of the relevant tensor networks modeling gravity that render them non-generic. We demonstrate this explicitly in random tensor network models of the python's lunch, where the exponential complexity is not generally controlled by the PLC exponent. We trace the difference with the PLC to a lack of "computational covariance" in random tensor networks: while the PLC is motivated by an ability to arbitrarily decompose space into low-complexity units provided certain basic rules are followed, we show that random tensor networks do not generically have this property. We propose another class of tensor networks built from what we call "twirled perfect tensors" that do satisfy the computational covariance property and have a complexity bounded by the PLC value. We still find a discrete limitation from local postselection that appears to be absent in gravity. Moreover, we show that this class of tensor networks combines desirable holographic features of perfect tensor networks and random tensor networks, for example, it obeys a lattice Ryu-Takayanagi formula for arbitrary boundary subregions. Though motivated by holography, these tensor networks provide a flexible framework with potential applications beyond quantum gravity.

Related papers

• Vectorized Symmetric and Fermionic Tensor Network Implementations for GPU-Accelerated Variational Monte Carlo [1.927845275055]
  Variational Monte Carlo calculations based on tensor networks (TN) have recently achieved competitive accuracy.<n>TN-VMC algorithms have not been formulated in a manner that can fully utilize GPU acceleration.<n>We show how to achieve vectorization for the practically relevant case of abelian symmetric tensor networks.
  arXiv  Detail & Related papers  (2026-08-28T03:10:41Z)
• Dense Neural Networks are not Universal Approximators [53.27010448621372]
  We show that dense neural networks do not possess universality of arbitrary continuous functions.<n>We consider ReLU neural networks subject to natural constraints on weights and input and output dimensions.
  arXiv  Detail & Related papers  (2026-02-07T16:52:38Z)
• Tensor Decomposition Networks for Fast Machine Learning Interatomic Potential Computations [48.46721044282335]
  tensor decomposition networks (TDNs) achieve competitive performance with dramatic speedup in computations.<n>We evaluate TDNs on PubChemQCR, a newly curated molecular relaxation dataset containing 105 million DFT-calculated snapshots.<n>Results show that TDNs achieve competitive performance with dramatic speedup in computations.
  arXiv  Detail & Related papers  (2025-07-01T18:46:27Z)
• Fermionic tensor network methods [0.0]
  We show how fermionic statistics can be naturally incorporated in tensor networks on arbitrary graphs through the use of graded Hilbert spaces. This formalism allows to use tensor network methods for fermionic lattice systems in a local way, avoiding the need of a Jordan-Wigner transformation or the explicit tracking of leg crossings by swap gates in 2D tensor networks.
  arXiv  Detail & Related papers  (2024-04-22T22:22:05Z)
• TensorKrowch: Smooth integration of tensor networks in machine learning [46.0920431279359]
  We introduceKrowch, an open source Python library built on top of PyTorch. Krowch allows users to construct any tensor network, train it, and integrate it as a layer in more intricate deep learning models.
  arXiv  Detail & Related papers  (2023-06-14T15:55:19Z)
• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout [3.38220960870904]
  We show how tree tensor networks (TTN) with CP rank constraints and tensor dropout can be used in machine learning.<n>A low-rank TTN classifier with branching ratio $b=4$ reaches a test set accuracy of 90.3% with low costs.<n>The number of parameters can be decreased and tuned more freely to control overfitting, improve computation properties, and reduce costs.
  arXiv  Detail & Related papers  (2023-05-30T22:22:24Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• On Optimizing the Communication of Model Parallelism [74.15423270435949]
  We study a novel and important communication pattern in large-scale model-parallel deep learning (DL) In cross-mesh resharding, a sharded tensor needs to be sent from a source device mesh to a destination device mesh. We propose two contributions to address cross-mesh resharding: an efficient broadcast-based communication system, and an "overlapping-friendly" pipeline schedule.
  arXiv  Detail & Related papers  (2022-11-10T03:56:48Z)
• Tensor Network States with Low-Rank Tensors [6.385624548310884]
  We introduce the idea of imposing low-rank constraints on the tensors that compose the tensor network. With this modification, the time and complexities for the network optimization can be substantially reduced. We find that choosing the tensor rank $r$ to be on the order of the bond $m$, is sufficient to obtain high-accuracy groundstate approximations.
  arXiv  Detail & Related papers  (2022-05-30T17:58:16Z)
• Lower and Upper Bounds on the VC-Dimension of Tensor Network Models [8.997952791113232]
  Network methods have been a key ingredient of advances in condensed matter physics. They can be used to efficiently learn linear models in exponentially large feature spaces. In this work, we derive upper and lower bounds on the VC dimension and pseudo-dimension of a large class of tensor network models.
  arXiv  Detail & Related papers  (2021-06-22T14:39:25Z)
• T-Basis: a Compact Representation for Neural Networks [89.86997385827055]
  We introduce T-Basis, a concept for a compact representation of a set of tensors, each of an arbitrary shape, which is often seen in Neural Networks. We evaluate the proposed approach on the task of neural network compression and demonstrate that it reaches high compression rates at acceptable performance drops.
  arXiv  Detail & Related papers  (2020-07-13T19:03:22Z)
• Approximation with Tensor Networks. Part I: Approximation Spaces [0.0]
  We study the approximation of functions by tensor networks (TNs) We show that Lebesgue $Lp$-spaces in one dimension can be identified with tensor product spaces of arbitrary order through tensorization. We show that functions in these approximation classes do not possess any Besov smoothness.
  arXiv  Detail & Related papers  (2020-06-30T21:32:59Z)
• On Infinite-Width Hypernetworks [101.03630454105621]
  We show that hypernetworks do not guarantee to a global minima under descent. We identify the functional priors of these architectures by deriving their corresponding GP and NTK kernels. As part of this study, we make a mathematical contribution by deriving tight bounds on high order Taylor terms of standard fully connected ReLU networks.
  arXiv  Detail & Related papers  (2020-03-27T00:50:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.