Visualizing Deep Network Training Trajectories with PCA

By Eliana Lorch, Thiel Fellowship. 2016

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Zheng Xu
2. Gavin Taylor
3. Tom Goldstein
4. Hao Li
5. Seyed Iman Mirzadeh
6. Alessandro Achille
7. Diganta Misra
8. Dacheng Tao

Citations in the corpus

• Visualizing the Loss Landscape of Neural Nets (2017, background): “Several authors have observed that random directions fail to capture the variation in optimization trajectories, including [10, 29, 28, 27].”