Structured pruning is a commonly used technique in deploying deep neural networks
(DNNs) onto resource-constrained devices. However, the existing pruning methods are …

The existing model compression methods via structured pruning typically require
complicated multi-stage procedures. Each individual stage necessitates numerous …

Transformers have become the state-of-the-art architectures for various tasks in Natural
Language Processing (NLP) and Computer Vision (CV); however, their space and …

We present a novel framework to train a large deep neural network (DNN) for only $\textit
{once} $, which can then be pruned to $\textit {any sparsity ratio} $ to preserve competitive …

Sparse linear models are one of several core tools for interpretable machine learning, a field
of emerging importance as predictive models permeate decision-making in many domains …

Abstract Model sparsification in deep learning promotes simpler, more interpretable models
with fewer parameters. This not only reduces the model's memory footprint and …

This paper proposes an algorithm (RMDA) for training neural networks (NNs) with a
regularization term for promoting desired structures. RMDA does not incur computation …

The increasing polarization of online political discourse calls for computational tools that
automatically detect and monitor ideological divides in social media. We introduce a …

Optimization problems with composite functions deal with the minimization of the sum of a
smooth function and a convex nonsmooth function. In this thesis several numerical methods …

Structured pruning is one of the most popular approaches to effectively compress the heavy
deep neural networks (DNNs) into compact sub-networks while retaining performance. The …