Implicit Bias of Gradient Descent on Linear Convolutional Networks
Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nati Srebro
–Neural Information Processing Systems
Consequently, optimization objectives for learning such high capacity models have many global minima that fit training data perfectly.
Neural Information Processing Systems
Feb-12-2026, 05:50:27 GMT
- Country:
- Asia > Middle East
- North America
- Canada > Quebec
- Montreal (0.04)
- United States (0.05)
- Canada > Quebec
- Technology: