We consider covariance estimation of any subgaussian distribution from finitely many iid
samples that are quantized to one bit of information per entry. Recent work has shown that a …

Quantization is a widely used compression method that effectively reduces redundancies in
over-parameterized neural networks. However, existing quantization techniques for deep …

Graph models and graph-based signals are becoming increasingly important in machine
learning, natural sciences, and modern signal processing. In this paper, we address the …

In this paper, we present a simple optimization-based preprocessing technique called
Weight Magnitude Reduction (MagR) to improve the performance of post-training …

Super-resolution semantic segmentation (SRSS) is a technique that aims to obtain high-
resolution semantic segmentation results based on resolution-reduced input images. SRSS …

We present a post-training quantization algorithm with error estimates relying on ideas
originating from frame theory. Specifically, we use first-order Sigma-Delta ($\Sigma\Delta $) …

Over the past few years, quantization has shown great and consistent success in
compressing high-dimensional data and over-parameterized models. This dissertation …