Landscape and training regimes in deep learning

Sep 6, 2022 · 1 min read
seminars

Event

Weekly DL Theory & Stat Phy Seminar

Short summary

In this seminar, I will talk about a line of works that tries to explain the phase transition behavior of the loss landscape (and the training dynamics as well) as the number of datas and parameters vary from a statistical physics point of view, namely, the jamming transition.

Papers

Paper discussed in the seminar:

  • Mario Geiger, Leonardo Petrini, and Matthieu Wyart. Landscape and training regimes in deep learning. In Physics Report 924:1-18, 2021.
Junghyun Lee
Authors
Junghyun Lee
PhD Candidate in Artificial Intelligence
PhD candidate at KAIST AI, jointly advised by Se-Young Yun and Chulhee Yun. I work on interactive machine learning, theoretical aspects of LLMs, learning/optimization theory, and statistical analysis of large networks.