all AI news
Depth Separation in Norm-Bounded Infinite-Width Neural Networks
Feb. 15, 2024, 5:41 a.m. | Suzanna Parkinson, Greg Ongie, Rebecca Willett, Ohad Shamir, Nathan Srebro
cs.LG updates on arXiv.org arxiv.org
Abstract: We study depth separation in infinite-width neural networks, where complexity is controlled by the overall squared $\ell_2$-norm of the weights (sum of squares of all weights in the network). Whereas previous depth separation results focused on separation in terms of width, such results do not give insight into whether depth determines if it is possible to learn a network that generalizes well even when the network width is unbounded. Here, we study separation in terms …
abstract arxiv complexity cs.lg insight network networks neural networks norm squares stat.ml study terms type
More from arxiv.org / cs.LG updates on arXiv.org
The Perception-Robustness Tradeoff in Deterministic Image Restoration
1 day, 20 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne