Metraipolis › archive › dc_eb86d8e2b2e1

Activation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression — arXiv:2610.10085

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10085
License (as archived)
CC0-1.0
Archived
2026-10-08T11:11:46.662Z
SHA-256 of the archived text
7ec548c58d13c2c3163bbc0daf668fc31e1e9baeee8546f9ff5641108f768c14
Stable URL of this page
https://metraipolis.com/documento/dc_eb86d8e2b2e1

How to cite

Activation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression — arXiv:2610.10085 — arXiv (en), https://arxiv.org/abs/2610.10085 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb86d8e2b2e1 (Metraipolis archive dc_eb86d8e2b2e1, sha256 7ec548c58d13c2c3163bbc0daf668fc31e1e9baeee8546f9ff5641108f768c14)
BibTeX
@misc{dceb86d8e2b2e1,
  title = {Activation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression — arXiv:2610.10085},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10085},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb86d8e2b2e1; sha256 7ec548c58d13c2c3163bbc0daf668fc31e1e9baeee8546f9ff5641108f768c14},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10085. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Post-training tensor-network compression replaces Transformer linear layers with Tensor Train (TT) or Tree Tensor Network (TTN) operators, but standard decompositions minimize weight-space Frobenius error rather than functional error under the layer's activation distribution. We propose Activation-aware Weight Tensorization (AWT), a training-free calibration wrapper that preconditions each weight matrix with a diagonal activation-derived scale before an unchanged TT/TTN solver and deploys the result with only an input-side elementwise rescaling. Across Llama 3.1 8B, Ministral 8B, and Qwen2.5 7B, AWT consistently improves vanilla TT/TTN tensorization at 2-6 times compression: under single-operator replacement, AWT closes 12-35% of the WikiText perplexity gap to the dense baseline across the three model families and 2-6 times compression settings; while under multi-operator Llama suffix replacement it closes 27-60% across attention-group and all-seven-matrix settings. The gains also transfer to downstream HellaSwag and ARC-Challenge evaluations. We further show that diagonal preconditioning is a robustness-modularity tradeoff rather than a diagonal-covariance assumption: a dense full-covariance oracle wins its own weighted objective in 80/81 cases, yet diagonal AWT gives better held-out functional fidelity in 53/81 cases. Together, these results position AWT as a principled, modular preconditioner for improving functional fidelity in fixed TT/TTN compression pipelines without modifying the decomposition solver.

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/2610.10085 — 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 2026-10-08T10:14:06.152Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).