Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
An Analytical Characterization of Sloppiness in Neural Networks: Insights from Linear Models
Jialin Mao, Itay Griniasty, Yan Sun +3
Recent experiments have shown that training trajectories of multiple deep neural networks with different architectures, optimization algorithms, hyper-parameter settings, and regul…
cs.LG2024
The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
Jialin Mao, Itay Griniasty, Han Kheng Teoh +5
We develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training. By examining the underlying high-dimensional probabilis…