.png){kind=icon}
.png){kind=icon}
Return
Computational Nonsmooth Analysis: Modern applications and recent developments [Special Issue on the Mathematics of Deep Learning]
.png){kind=icon}
PRE
AI
L
A
DOI：10.1109/MSP.2026.3662660.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Neural networks (NNs) have transformed the field of artificial intelligence, showcasing remarkable abilities in learning complex representations, scaling to large datasets, and driving advancements across a wide range of applications. The training of these networks often involves optimizing functions that are not only nonconvex but possibly also nonsmooth, which introduces significant challenges in algorithm design and analysis. In this article, we provide an overview of recent advancements in the theoretical and computational aspects of nonsmooth optimization, thereby highlighting an area of growing importance that we refer to as “computational nonsmooth analysis.” We also demonstrate the relevance of these advancements in some representative applications. Lastly, we discuss some fundamental open questions in this area, the answers to which will impact the use and understanding of nonsmooth models in modern deep learning and signal processing.
Keywords:
Neural networks
Artificial intelligence
Computational modeling
Deep learning
Training
Optimization models
Signal processing algorithms
Gradient methods
Smoothing methods
Artificial neural networks
Journal
IF:
9.6
Papers:
1.1W
Citations:
1.7W
Organization
Cited Papers