Pith. sign in

REVIEW 2 cited by

Rademacher Random Projections with Tensor Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2110.13970 v3 pith:IRMXBJGC submitted 2021-10-26 cs.LG stat.ML

Beheshteh T. Rakhshan , Guillaume Rabusseau This is my paper · ORCID
classification cs.LGstat.ML
keywords rademacherrandomtensortensorizedprojectioncoredistributiondrawn
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Random projection (RP) have recently emerged as popular techniques in the machine learning community for their ability in reducing the dimension of very high-dimensional tensors. Following the work in [30], we consider a tensorized random projection relying on Tensor Train (TT) decomposition where each element of the core tensors is drawn from a Rademacher distribution. Our theoretical results reveal that the Gaussian low-rank tensor represented in compressed form in TT format in [30] can be replaced by a TT tensor with core elements drawn from a Rademacher distribution with the same embedding size. Experiments on synthetic data demonstrate that tensorized Rademacher RP can outperform the tensorized Gaussian RP studied in [30]. In addition, we show both theoretically and experimentally, that the tensorized RP in the Matrix Product Operator (MPO) format is not a Johnson-Lindenstrauss transform (JLT) and therefore not a well-suited random projection map

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Faster Linear Algebra Algorithms with Structured Random Matrices

    cs.DS 2025-08 accept novelty 8.0 of 10

    Randomized sketching needs only the new OSI property, not the full subspace embedding, and multiple structured matrices satisfy it with near-optimal cost.

  2. Compressed Bayesian Tensor Regression

    stat.ME 2025-10 reject novelty 6.0 of 10

    Compressed Bayesian tensor regression uses random projections to shrink tensor inputs before a low-rank Bayesian fit, reporting better out-of-sample forecasts at lower computational cost than uncompressed tensor regression.

Pith tools