2012 NASAAchievingLowerRegretsandFas

From GM-RKB
Jump to: navigation, search

Subject Headings:

Notes

Cited By

Quotes

Author Keywords

Abstract

The classic Stochastic Approximation (SA) method achieves optimal rates under the black-box model. This optimality does not rule out better algorithms when more information about functions and data is available.

We present a family of Noise Adaptive Stochastic Approximation (NASA) algorithms for online convex optimization and stochastic convex optimization. NASA is an adaptive variant of Mirror Descent Stochastic Approximation. It is novel in its practical variation-dependent stepsizes and better theoretical guarantees. We show that comparing with state-of-the-art adaptive and non-adaptive SA methods, lower regrets and faster rates can be achieved under low-variation assumptions.

References

;

 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2012 NASAAchievingLowerRegretsandFasHua Ouyang
Alexander Gray
NASA: Achieving Lower Regrets and Faster Rates via Adaptive Stepsizes10.1145/2339530.23395572012