Mathematical Challenges in Deep Learning
Machine Learning
2023-03-29 v1 Artificial Intelligence
Statistics Theory
Machine Learning
Statistics Theory
Abstract
Deep models are dominating the artificial intelligence (AI) industry since the ImageNet challenge in 2012. The size of deep models is increasing ever since, which brings new challenges to this field with applications in cell phones, personal computers, autonomous cars, and wireless base stations. Here we list a set of problems, ranging from training, inference, generalization bound, and optimization with some formalism to communicate these challenges with mathematicians, statisticians, and theoretical computer scientists. This is a subjective view of the research questions in deep learning that benefits the tech industry in long run.
Cite
@article{arxiv.2303.15464,
title = {Mathematical Challenges in Deep Learning},
author = {Vahid Partovi Nia and Guojun Zhang and Ivan Kobyzev and Michael R. Metel and Xinlin Li and Ke Sun and Sobhan Hemati and Masoud Asgharian and Linglong Kong and Wulong Liu and Boxing Chen},
journal= {arXiv preprint arXiv:2303.15464},
year = {2023}
}