Learning relevant features of data with multi-scale tensor networks
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Abstract Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorithm, then optimizing just the top layer for supervised classification of the MNIST and fashion MNIST data sets gives very good results. We also discuss mixing a prior guess for supervised weights together with an unsupervised representation of the data, yielding a smaller number of features nevertheless able to give good performance.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Density matrix formulation for quantum renormalization groups
White, S. R. (1992) · Physical Review Letters · doi:10.1103/physrevlett.69.2863 · Cited by 7,702 · cited 1×
“(DMRG) algorithm used in quantum mechanics, where the Φj is analogous to an ensemble of wavefunctions enumerated by j; ρ is the full density matrix; and ρ12 is a reduced density matrix [24].”
MethodFashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108
The density-matrix renormalization group in the age of matrix product states
Schollwöck, U. (2011) · Annals of Physics · doi:10.1016/j.aop.2010.09.012 · Cited by 4,818 · cited 2×
“A solution that is both practical and interesting is to assume that the optimal weights W can be efficiently approximated by a tensor network [12, 28], an idea proposed recently by several groups [4–6, 36].”
BackgroundThe density-matrix renormalization group
Schollwöck, U. (2005) · Reviews of Modern Physics · doi:10.1103/revmodphys.77.259 · Cited by 3,323
Efficient Classical Simulation of Slightly Entangled Quantum Computations
Vidal, G. (2003) · Physical Review Letters · doi:10.1103/physrevlett.91.147902 · Cited by 2,368
Orús, R. (2014) · Annals of Physics · doi:10.1016/j.aop.2014.06.013 · Cited by 2,255 · cited 3×
“Tensor networks break the curse of dimensionality by allowing operations such as contracting very high-order tensors or retrieving their components to be accomplished with polynomial cost by manipulating the low-order factor tensors [12].”
BackgroundFinitely correlated states on quantum spin chains
Fannes, M., Nachtergaele, B., & Werner, R. F. (1992) · Communications in Mathematical Physics · doi:10.1007/bf02099178 · Cited by 1,422
Thermodynamic limit of density matrix renormalization.
Östlund, S., & Rommer, S. (1995) · Physical Review Letters · doi:10.1103/physrevlett.75.3537 · Cited by 1,077
Entanglement renormalization and holography
Swingle, B. (2012) · Physical Review D · doi:10.1103/physrevd.86.065007 · Cited by 915 · cited 1×
“[33] Brian Swingle, “Entanglement renormalization and holography,” Phys.”
Tensor decompositions for learning latent variable models
(2012) · arXiv (Cornell University) · doi:10.5555/2627435.2697055 · Cited by 779 · cited 2×
“Tensor decompositions are proving to be a powerful tool for machine learning, with applications in a wide variety of contexts from optimization algorithms [1, 2], to compression of weight parameters [3–9], to theories of model expressivity and inductive bias [4, 10].”
Background
Cited by
Machine learning and the physical sciences
Carleo, G., Cirac, I., Cranmer, K., Daudet, L., Schuld, M., Tishby, N., Vogt-Maranto, L., & Zdeborová, L. (2019) · Reviews of Modern Physics · doi:10.1103/revmodphys.91.045002 · Cited by 2,417
The ITensor Software Library for Tensor Network Calculations
Fishman, M., White, S., & Stoudenmire, E. M. (2022) · SciPost Physics Codebases · doi:10.21468/scipostphyscodeb.4 · Cited by 1,084
“Machine learning is an area where ITensor has potential to be used much more in the future, and ITensor has already been used to investigate new models and algorithms for machine learning, including supervised [63, 64] and unsupervised [65] learning using models parameterized by tensor networks, and to investigate gen…”
MethodSelf-citationTensor networks for complex quantum systems
Orús, R. (2019) · Nature Reviews Physics · doi:10.1038/s42254-019-0086-7 · Cited by 569
Towards quantum machine learning with tensor networks
Huggins, W., Patil, P., Mitchell, B., Whaley, K. B., & Stoudenmire, E. M. (2019) · Quantum Science and Technology · doi:10.1088/2058-9565/aaea94 · Cited by 366
Self-citationUnsupervised Generative Modeling Using Matrix Product States
Han, Z.-Y., Wang, J., Fan, H., Wang, L., & Zhang, P. (2018) · Physical Review X · doi:10.1103/physrevx.8.031012 · Cited by 256
Metadata
- Authors
- Stoudenmire, E. M.
- Venue
- Quantum Science and Technology
- Publisher
- IOP Publishing
- Published
- 2018-04-25
- Volume
- 3
- Issue
- 3
- Pages
- 034003
- ISSN
- 2058-9565 (ISSN-L)
- OpenAlex
- W2782213776
- Cited by
- 102
- References
- 13
- FWCI
- 5.94
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning relevant features of data with multi-scale tensor networks. https://app.cochat.ai/papers/10.1088/2058-9565/aaba1a
- The paper
- Stoudenmire, E. M. (2018). Learning relevant features of data with multi-scale tensor networks. Quantum Science and Technology. https://doi.org/10.1088/2058-9565/aaba1a
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.