Unveiling Hidden Convexity in Deep Learning: a Sparse Signal Processing Perspective
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911543238590464 |
|---|---|
| author | Zeger, Emi Pilanci, Mert |
| author_facet | Zeger, Emi Pilanci, Mert |
| contents | Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognition, audio processing, and language modeling. Despite this success, the non-convex nature of DNN loss functions complicates optimization and limits theoretical understanding. In this paper, we highlight how recently developed convex equivalences of ReLU NNs and their connections to sparse signal processing models can address the challenges of training and understanding NNs. Recent research has uncovered several hidden convexities in the loss landscapes of certain NN architectures, notably two-layer ReLU networks and other deeper or varied architectures. This paper seeks to provide an accessible and educational overview that bridges recent advances in the mathematics of deep learning with traditional signal processing, encouraging broader signal processing applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23831 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unveiling Hidden Convexity in Deep Learning: a Sparse Signal Processing Perspective Zeger, Emi Pilanci, Mert Machine Learning Signal Processing Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognition, audio processing, and language modeling. Despite this success, the non-convex nature of DNN loss functions complicates optimization and limits theoretical understanding. In this paper, we highlight how recently developed convex equivalences of ReLU NNs and their connections to sparse signal processing models can address the challenges of training and understanding NNs. Recent research has uncovered several hidden convexities in the loss landscapes of certain NN architectures, notably two-layer ReLU networks and other deeper or varied architectures. This paper seeks to provide an accessible and educational overview that bridges recent advances in the mathematics of deep learning with traditional signal processing, encouraging broader signal processing applications. |
| title | Unveiling Hidden Convexity in Deep Learning: a Sparse Signal Processing Perspective |
| topic | Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2603.23831 |