On the Universality of Online Mirror Descent

Srebro, Nati, Sridharan, Karthik, Tewari, Ambuj

Dec-31-2011–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.

artificial intelligence, machine learning, mirror descent, (17 more...)

Neural Information Processing Systems

Dec-31-2011

Conferences PDF

Country:
- Asia > Middle East
  - Israel (0.14)
- North America > United States
  - Texas (0.14)

Industry:
- Education (0.58)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.47)

Duplicate Docs Excel Report

Title
On the Universality of Online Mirror Descent

Similar Docs Excel Report more

Title	Similarity	Source
None found