Simultaneously considering multiple objectives in machine learning has been a popular
approach for several decades, with various benefits for multi-task learning, the consideration …

Abstract Lottery Ticket Hypothesis (LTH)[14] has gathered great focus since being proposed.
Researchers then succeed in figuring out alternative ways to find the” winning ticket” and …

Sparsity is a highly desired feature in deep neural networks (DNNs) since it ensures
numerical efficiency, improves the interpretability of models (due to the smaller number of …

Pruning at initialization and training a sparse network from scratch (sparse training) become
increasingly popular. However, most sparse training literature addresses only the …

Large transformers have demonstrated remarkable success, making it necessary to
compress these models to reduce inference costs while preserving their perfor-mance …

The great success of deep neural networks is built upon their over-parameterization, which
smooths the optimization landscape without degrading the generalization ability. Despite the …

We propose a novel sparsity learning framework called from the perspective of differential
inclusion, which enjoys better statistical properties and computational efficiency. Utility of this …

This paper studies the task of budgeted network learning [35] that aims at discovering good
convolutional network structures under parameters/FLOPs constraints. Particularly, we …

The Coronavirus disease 2019 (COVID-19) has affected several million people. With the
outbreak of the epidemic, many researchers are devoting themselves to the COVID-19 …

Different levels of visual information are generally coupled in image data, thus making it
hard to reverse the trend of deep learning models that learn texture bias from images …