On the Universality of Online Mirror Descent

Srebro, Nati, Sridharan, Karthik, Tewari, Ambuj

Feb-15-2020, 00:11:51 GMT–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. Papers published at the Neural Information Processing Systems Conference.

artificial intelligence, descent, machine learning, (2 more...)

Neural Information Processing Systems

Feb-15-2020, 00:11:51 GMT

Conferences Web Page

Add feedback

Industry:
- Education > Focused Education > Special Education (0.47)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning (1.00)