Output-Space Allocation Costs for Calibration-Guided LLM Compression: An Empirical Study

arXiv:2606.27785v1 Announce Type: new Abstract: Training-free compression methods for large language models (LLMs) often use calibration data to guide compression decisions. ROCKET, a recent method combining sparse-dictionary factorization with multi-choice knapsack problem (MCKP) allocation, derives its per-layer factorization from an output reconstruction objective but uses weight-space Frobenius error as the MCKP allocation cost. We investigate whether aligning the allocation cost with the ou...