← 研踪 PaperTrailarXiv:2611.11967 · v1
Pairwise distortion distribution for compression and quantization
首次提交 2026-11-09 14:50
版本更新 2026-11-09 14:50
雷达观测 2026-11-10 13:18
摘要
Choosing the latent dimension is a critical challenge in data compression, where conventional hyperparameter optimization is costly and ad hoc. Intrinsic dimension provides a good alternative, which connects information-theoretic notions such as Renyi information dimension (RID) to rate-distortion dimension and random codebook compression. In this work, we introduce the pairwise distortion distribution (PDD) and its asymptotic limit, pairwise dimension (PD), which generalize the correlation integral to general distortion measures. We show that PD bounds RID, and PDD provides a lower bound for random codebook quantization performance, which can guide a practical use for compression, quantization, and dimensionality reduction applications.
期刊信息：ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-09 14:50 · 最新观测版本
Pairwise distortion distribution for compression and quantization
Choosing the latent dimension is a critical challenge in data compression, where conventional hyperparameter optimization is costly and ad hoc. Intrinsic dimension provides a good alternative, which connects information-theoretic notions such as Renyi information dimension (RID) to rate-distortion dimension and random codebook compression. In this work, we introduce the pairwise distortion distribution (PDD) and its asymptotic limit, pairwise dimension (PD), which generalize the correlation integral to general distortion measures. We show that PD bounds RID, and PDD provides a lower bound for random codebook quantization performance, which can guide a practical use for compression, quantization, and dimensionality reduction applications.
查看此版本解读 →查看此版本原文 ↗