Metraipolis › archive › dc_548c21059468
Lightweight Representation Learning for Low Tucker Rank Tensors — arXiv:2611.01168
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01168
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:56:29.478Z
- SHA-256 of the archived text
56da21ca508ff18ff6b45df7949c8bf506f3040e584c74b32cd3b922be79938f- Stable URL of this page
https://metraipolis.com/documento/dc_548c21059468
How to cite
Lightweight Representation Learning for Low Tucker Rank Tensors — arXiv:2611.01168 — arXiv (en), https://arxiv.org/abs/2611.01168 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_548c21059468 (Metraipolis archive dc_548c21059468, sha256 56da21ca508ff18ff6b45df7949c8bf506f3040e584c74b32cd3b922be79938f)
BibTeX
@misc{dc548c21059468,
title = {Lightweight Representation Learning for Low Tucker Rank Tensors — arXiv:2611.01168},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01168},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_548c21059468; sha256 56da21ca508ff18ff6b45df7949c8bf506f3040e584c74b32cd3b922be79938f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01168. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Low Tucker rank tensors provide compact representations of multidimensional dependencies, but standard learning pipelines can incur substantial computational and memory overhead from redundant intermediate quantities. We reduce this overhead without modifying the underlying representation objective or parameterization. Our approach combines three complementary components: (i) sequential extraction of only task-required spectral components, avoiding unnecessary full decompositions; (ii) factor-wise multilinear contractions without materializing large Kronecker operators; and (iii) compact latent-state updates without storing full ambient tensor iterates. These components preserve the algebraic operations and learning trajectories of the original algorithms while reducing their computational and memory footprints. Across five low Tucker rank tensor estimators, our implementations match the original trajectories to numerical precision (relative discrepancies of $10^{-16}$ to $10^{-13}$), while reducing per-iteration runtime by up to $3.12\times$ and resident memory by up to $616\times$ ($99.8\%$) on the main order-3 benchmark at $n=100$, with memory reductions exceeding $900\times$ across the full evaluation suite. These results show that substantial computational redundancy can be eliminated from Tucker representation learning without changing the underlying model or learned representation.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01168 — 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 2026-11-03T10:49:38.533Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).