Skip to content

Ablation, Statistical Inference, and Validation for KV-Cache Compression

Paolo D'Alberto, Ashish Siarasao, Elliott Delaye, Rajeev Patwari

cs.LGarXiv:2607.09683

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 (deff) adapting to calibration budgets rather than true data rank. (this is an abstract of the abstract thank you )

Create a lesson

Paper details

Categories: cs.LG, cs.AI, cs.IT, math.IT

15 pages, 8 figures, minimum number of citations