Ablation, Statistical Inference, and Validation for KV-Cache Compression
This paper systematically compares Turbo-Quant and SpectralQuant KV-cache compression methods using a statistical validation methodology that separates systematic codec differences from implementation variance. Key findings reveal that eigenbasis-based methods fail on heavy-tailed data due to covariance instability but excel in structured regimes, with the effective semantic dimension adapting to calibration budgets rather than true data rank.
-->
[Submitted on 14 Jun 2026]
Title:Ablation, Statistical Inference, and Validation for KV-Cache Compression
View a PDF of the paper titled Ablation, Statistical Inference, and Validation for KV-Cache Compression, by Paolo D'Alberto and 2 other authors
View PDF HTML (experimental)
Abstract:This study systematically compares Turbo-Quant and SpectralQuant KV-cache compression, evaluating non-dominated schemes, including WHT rotation with Beta Lloyd-Max and QJL, through a statistical validation methodology that separates systematic codec differences from implementation variance. Key findings reveal that while eigenbasis-based methods fail on heavy-tailed data due to covariance instability, they excel in structured regimes, with the effective semantic dimension ($d_{eff}$) adapting to calibration budgets rather than true data rank. (this is an abstract of the abstract thank you )
Comments: 15 pages, 8 figures, minimum number of citations
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Information Theory (cs.IT)
Cite as: arXiv:2607.09683 [cs.LG]
(or arXiv:2607.09683v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.09683
arXiv-issued DOI via DataCite
Submission history
From: Paolo D'Alberto [view email] [v1] Sun, 14 Jun 2026 22:44:55 UTC (1,852 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Ablation, Statistical Inference, and Validation for KV-Cache Compression, by Paolo D'Alberto and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-07
Change to browse by:
cs cs.AI cs.IT math math.IT
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)