4 accepted papers
This paper considers the problem of converting a given dense linear layer into a low-precision version. The tradeoff between minimizing description length and discrepancy introduced at the output of the layer is analyzed information theoretically (IT). It is shown that the popular GPTQ algorithm may…
Post-training quantization (PTQ) has emerged as a critical technique for efficient deployment of large language models (LLMs). This work proposes NestQuant, a novel PTQ scheme for weights and activations that is based on self-similar nested lattices. Recent works have mathematically shown such quan…
In a growing number of applications, there is a need to digitize a (possibly high) number of correlated signals whose spectral characteristics are challenging for traditional analog-to-digital converters (ADCs). Examples, among others, include multiple-input multiple-output systems where the ADCs mu…
Consider the rank-1 spiked model: $\bf{X}=\sqrt{\nu}\xi \bf{u}+ \bf{Z}$, where $\nu$ is the spike intensity, $\bf{u}\in\mathbb{S}^{k-1}$ is an unknown direction and $\xi\sim \mathcal{N}(0,1),\bf{Z}\sim \mathcal{N}(\bf{0},\bf{I})$. Motivated by recent advances in analog-to-digital conversion, we stud…