Visualizing the Loss Landscape of Neural Nets

By Hao Li, Zheng Xu, Gavin Taylor, Tom Goldstein. 2017

2,377 citations recorded by the source corpus.

Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and well-chosen training parameters (batch size, learning rate, optimizer) produce minimizers that generalize better. However, the reasons for these differences, and their effects on the underlying loss landscape, are not well understood. In this paper, we explore the structure of neural loss functions, and the effect of loss landscapes on generalization, using a range of visualization methods. First, we introduce a simple "filter normalization" method that helps us visualize loss function curvature and make meaningful side-by-side comparisons between loss functions. Then, using a variety of visualizations, we explore how network architecture affects the loss landscape, and how training parameters affect the shape of minimizers.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Optimization & Training, Scaling & Learning Theory

How researchers see this paper

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

In Artificial Intelligence

  1. Yoshua Bengio
  2. Jianfeng Gao
  3. Mohit Bansal
  4. Quoc V. Le
  5. Percy Liang
  6. Sergey Levine
  7. Dacheng Tao
  8. Ruslan Salakhutdinov

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Trevor Darrell
  4. Ming-Hsuan Yang
  5. Xiaogang Wang
  6. Bernt Schiele
  7. Jitendra Malik
  8. Alan L. Yuille

In Optimization & Training

  1. Martin Jaggi
  2. Simon Lacoste-Julien
  3. Sebastian U. Stich
  4. Peter Richtárik
  5. Frank Hutter
  6. Quoc V. Le
  7. Yoshua Bengio
  8. Michael I. Jordan

In Scaling & Learning Theory

  1. Andrew Gordon Wilson
  2. Michael W. Mahoney
  3. Stefano Soatto
  4. Charles H. Martin
  5. Pavel Izmailov
  6. Samet Oymak
  7. Alessandro Achille
  8. Hanie Sedghi

Citations in the corpus