REVIEW 5 cited by
Era of Big Data Processing: A New Approach via Tensor Networks and Tensor Decompositions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Many problems in computational neuroscience, neuroinformatics, pattern/image recognition, signal processing and machine learning generate massive amounts of multidimensional data with multiple aspects and high dimensionality. Tensors (i.e., multi-way arrays) provide often a natural and compact representation for such massive multidimensional data via suitable low-rank approximations. Big data analytics require novel technologies to efficiently process huge datasets within tolerable elapsed times. Such a new emerging technology for multidimensional big data is a multiway analysis via tensor networks (TNs) and tensor decompositions (TDs) which represent tensors by sets of factor (component) matrices and lower-order (core) tensors. Dynamic tensor analysis allows us to discover meaningful hidden structures of complex data and to perform generalizations by capturing multi-linear and multi-aspect relationships. We will discuss some fundamental TN models, their mathematical and graphical descriptions and associated learning algorithms for large-scale TDs and TNs, with many potential applications including: Anomaly detection, feature extraction, classification, cluster analysis, data fusion and integration, pattern recognition, predictive modeling, regression, time series analysis and multiway component analysis. Keywords: Large-scale HOSVD, Tensor decompositions, CPD, Tucker models, Hierarchical Tucker (HT) decomposition, low-rank tensor approximations (LRA), Tensorization/Quantization, tensor train (TT/QTT) - Matrix Product States (MPS), Matrix Product Operator (MPO), DMRG, Strong Kronecker Product (SKP).
Forward citations
Cited by 5 Pith papers
-
Secant varieties of toric varieties arising from simplicial complexes
Secants of simplicial toric embeddings are toric, enabling a complete classification of the Gorenstein and singular behavior of secants of Segre-Veronese varieties.
-
AMPED: Accelerating MTTKRP for Billion-Scale Sparse Tensor Decomposition on Multiple GPUs
AMPED partitions sparse tensors by output-mode index to run MTTKRP on multiple GPUs, reporting a 5.1x geometric mean speedup over single-GPU baselines on billion-scale tensors.
-
Efficient Contraction of Large Tensor Networks for Weighted Model Counting through Graph Decompositions
A tree-decomposition-guided factoring method produces tensor contraction orders with max rank at most ceil(4(w+1)/3), improving the prior 3(w+2) bound and yielding a competitive weighted model counter.
-
Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks
The paper makes the case that tensorized neural networks offer valuable compression, scaling, and interpretability advantages that the deep learning community has not yet fully exploited.
-
Deep Tree Tensor Networks
DTTN is a multilinear, activation-free architecture built from antisymmetric interaction modules that reaches 82.4% top-1 accuracy on ImageNet-1k and is claimed to unfold into a tree tensor network.
Discussion (0). Continue with ORCID to comment.