Abstract
We provide a detailed asymptotic study of gradient flow trajectories and their implicit optimization bias when minimizing the exponential loss over “diagonal linear networks”. This is the simplest model displaying a transition between “kernel” and non-kernel (“rich” or “active”) regimes. We show how the transition is controlled by the relationship between the initialization scale and how accurately we minimize the training loss. Our results indicate that some limit behaviors of gradient descent only kick in at ridiculous training accuracies (well beyond 10-100). Moreover, the implicit bias at reasonable initialization scales and training accuracies is more complex and not captured by these limits.
Original language | English (US) |
---|---|
Journal | Advances in Neural Information Processing Systems |
Volume | 2020-December |
State | Published - 2020 |
Event | 34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online Duration: Dec 6 2020 → Dec 12 2020 |
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Information Systems
- Signal Processing