3 papers
cs.LG2026
Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization
Samy Houache, Yann Traonmilin, Jean-François Aujol
Mixed-precision post-training quantization is a network compression method that assigns bits layer by layer, under a global memory budget using a small calibration set. The main di…
math.FA2026
Schäffer's matrix inequality: the exact asymptotic constant
Samy Houache, Oleg Szehr, Rachid Zarouf
Let denote the smallest constant such that \[ |\det T|\|T^{-1}\| \leq S_n \|T\|^{n-1} \] for every invertible operator on every -dimensional complex Banach space. In H…
cs.IT2025
On the impact of the parametrization of deep convolutional neural networks on post-training quantization
Samy Houache, Jean François Aujol, Yann Traonmilin
This paper introduces novel theoretical approximation bounds for the output of quantized neural networks, with a focus on convolutional neural networks (CNN). By considering layerw…