Adaptive Methods for Nonconvex Optimization
Manzil Zaheer, Sashank Reddi, Devendra Sachan, Satyen Kale, Sanjiv Kumar
–Neural Information Processing Systems
The first prominent algorithms in this line of research isADAGRAD [7,22], which uses a per-dimension learning rate based on squared pastgradients.ADAGRADachievedsignificant performance gainsincomparison toSGDwhenthe gradientsaresparse.
Neural Information Processing Systems
Feb-13-2026, 17:37:30 GMT
- Country:
- Asia
- Middle East > Jordan (0.04)
- Vietnam > Da Nang
- Da Nang (0.04)
- Europe > Spain (0.04)
- North America
- Canada > Quebec
- Montreal (0.04)
- United States
- California > Santa Clara County
- Palo Alto (0.04)
- New York (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- California > Santa Clara County
- Canada > Quebec
- Asia
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Education (0.69)
- Technology: