Metraipolis › archive › dc_6f447fb7a571

Improving TensorSketch Using Complex Random Variables — arXiv:2608.10523

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10523
License (as archived)
CC0-1.0
Archived
2026-10-19T06:09:13.961Z
SHA-256 of the archived text
2602399bc8f7b17562574d33f2b8a74bac69640d2bf10a5a2587121d5753245f
Stable URL of this page
https://metraipolis.com/documento/dc_6f447fb7a571

How to cite

Improving TensorSketch Using Complex Random Variables — arXiv:2608.10523 — arXiv (en), https://arxiv.org/abs/2608.10523 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6f447fb7a571 (Metraipolis archive dc_6f447fb7a571, sha256 2602399bc8f7b17562574d33f2b8a74bac69640d2bf10a5a2587121d5753245f)
BibTeX
@misc{dc6f447fb7a571,
  title = {Improving TensorSketch Using Complex Random Variables — arXiv:2608.10523},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10523},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6f447fb7a571; sha256 2602399bc8f7b17562574d33f2b8a74bac69640d2bf10a5a2587121d5753245f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10523. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

\texttt{TensorSketch} by~\cite{pham2013fast,kar2012random} provides efficient sketching algorithms for high-dimensional polynomial kernels $\vec{x}^{\otimes p} \in \R^{d^p}$. \cite{kar2012random} uses dense Johnson-Lindenstrauss (JL)-type projections with computational cost $O(pDd)$, where $D$ denotes the sketch dimension, whereas~\cite{pham2013fast} extends the sparse \texttt{CountSketch}~\citep{count_sketch} algorithm, yielding a faster algorithm for high-dimensional sparse inputs with running time $O\big(p(\nnz{\vec{x}} + D \log D)\big)$. However, the variance of both estimators grows exponentially with the polynomial degree $p$, scaling as $3^{p}/D$. Recent work by~\cite{pmlr-v206-wacker23a} showed that using complex-valued distribution reduces this dependence to $2^{p}/D$ for the approach of~\cite{kar2012random}. However, their method relies on dense JL-type projections with computational cost $O(pDd)$ and does not extend to the algorithm of~\cite{pham2013fast}. In this work, we introduce a simple variant of \texttt{TensorSketch}~\citep{pham2013fast} that achieves the same variance bound as~\cite{pmlr-v206-wacker23a}, while retaining its advantage of the input-sparsity running time. We validate our results with supporting experiments on synthetic and real-world datasets.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Data Structures and Algorithms (cs.DS) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.10523 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T05:57:28.375Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).