ADOPT: Modified Adam Can Converge with Any β 2 with the Optimal Rate Keno Harada The University of Tokyo
–Neural Information Processing Systems
Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., β
Neural Information Processing Systems
Mar-23-2025, 07:08:30 GMT
- Country:
- Asia > Japan
- Honshū > Kantō > Tokyo Metropolis Prefecture > Tokyo (0.41)
- North America > Canada (0.28)
- Asia > Japan
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (1.00)
- Research Report
- Technology: