On the Universality of Online Mirror Descent
–Neural Information Processing Systems
We show that for a general class of convex online learning problems, Mirror Descent can always achieve a (nearly) optimal regret guarantee.
Neural Information Processing Systems
Mar-15-2024, 07:59:39 GMT
- Country:
- North America > United States
- Texas > Travis County > Austin (0.04)
- Europe > Russia
- Central Federal District > Moscow Oblast > Moscow (0.04)
- Asia > Middle East
- Israel > Jerusalem District > Jerusalem (0.04)
- North America > United States
- Industry:
- Education (0.58)
- Technology: