[Paper Reading] Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
🗓
For mobile: View PDF
Main References
- Arthur Jacot. Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions. ICLR 2023.
Hanseul Cho
Student Researcher in Google NYC. PhD Student at OptiML Lab in KAIST AI. Working on ML/DL/Opt+Theory and Language Models.
- 📍 New York City, NY, United States
- 📝 CV
- Github
- Google Scholar
- Semantic Scholar
- ORCID
You May Also Enjoy
[Paper Reading] PENCIL: Long Thoughts with Short Memory
🗓
📌 Presented in OptiML Group Meeting (Spring 2025)
[Ph.D. Thesis Proposal] Unraveling and Overcoming Challenges in Machine Learning: Generalizability, Adaptability, and Multifacetedness
🗓
📌 Proposed for Ph.D. Candidacy Exam @ KAIST AI
[Paper Reading] Viewing Log-Depth Transformers via the Lens of Distributed Computing
🗓
📌 Presented in OptiML Group Meeting (Fall 2024)
[Paper Reading] StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization
🗓
📌 Presented in OptiML Group Meeting (Summer 2024)