paper-with-me

Papers

Non-asymptotic quantisation of spherically symmetric distributions

2026-05-12 · Luc Pronzato, Anatoly Zhigljavsky arxiv

Zador's celebrated theorem is a cornerstone of optimal quantisation, establishing both the weak limit of the empirical distribution of an $n$-point optimal quantiser in $R^d$ and the decay rate of the associated $L_s$-mean quantisation error. However, for large dimensions $d$, observing this asymptotic behaviour demands an astronomically large sample size $n$, which grows super-exponentially with $d$. Through a detailed analysis of the quantisation problem for spherically symmetric distributions, we demonstrate that for moderate $n$ random quantisers uniformly distributed on a sphere of suitable radius $r$ achieve exceptional performance. The expected distortion, expressed as a triple integral, can be computed with arbitrary precision, and the optimal radius $r$ can be efficiently determined numerically. Leveraging results from extreme-value theory, we derive approximations for $r$, particularly in scenarios where $n$ scales with $d$. Depending on the growth rate of $n$, $r$ may either converge to zero or approach a limiting value that is independent of $s$.

📄 PDF Abstract BibTeX arXiv:2605.12568

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Analytical Expression for Spherically Symmetric Photoacoustic Sources: A Unified General Solution (Theoretical Analysis and Derivation)

2026-01-12 · Shuang Li, Yibing Wang, Yu Zhang, Changhui Li arxiv

Here we present a comprehensive derivation of the analytical expression for the spatiotemporal acoustic pressure generated by photoacoustic sources with spherically symmetric initial pressure distributions. Starting from…

Hierarchical Modeling of Local Image Features through L_p-Nested Symmetric Distributions

2009-12-01 · NeurIPS 2009 12 · Matthias Bethge, Eero P. Simoncelli, Fabian H. Sinz

We introduce a new family of distributions, called $L_p${\em -nested symmetric distributions}, whose densities access the data exclusively through a hierarchical cascade of $L_p$-norms. This class generalizes the family …

lp-Recovery of the Most Significant Subspace among Multiple Subspaces with Outliers

2010-12-18 · Gilad Lerman, Teng Zhang

We assume data sampled from a mixture of d-dimensional linear subspaces with spherically symmetric distributions within each subspace and an additional outlier component with spherically symmetric distribution within the…

A Study of Quantisation-aware Training on Time Series Transformer Models for Resource-constrained FPGAs

2023-10-04 · Tianheng Ling, Chao Qian, Lukas Einhaus, Gregor Schiele

This study explores the quantisation-aware training (QAT) on time series Transformer models. We propose a novel adaptive quantisation scheme that dynamically selects between symmetric and asymmetric schemes during the QA…

Time Series

Faster Directional Convergence of Linear Neural Networks under Spherically Symmetric Data

2021-12-01 · NeurIPS 2021 12 · Dachao Lin, Ruoyu Sun, Zhihua Zhang

In this paper, we study gradient methods for training deep linear neural networks with binary cross-entropy loss. In particular, we show global directional convergence guarantees from a polynomial rate to a linear rate f…