Visualizing the Loss Landscape of Neural Nets
This provides insights for machine learning researchers into how design choices affect optimization, but it is incremental as it builds on existing visualization techniques.
The paper tackled the problem of understanding why certain neural network architectures and training parameters lead to easier training and better generalization by visualizing the loss landscape. They introduced a filter normalization method to compare loss functions and found that skip connections produce smoother landscapes, with a 15% reduction in sharpness compared to standard architectures.
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.