Noise Adaptive Stochastic Approximation
Jump to navigation
Jump to search
A Noise Adaptive Stochastic Approximation is a stochastic approximation algorithm developed by Ouyang & Gray, 2012.
- AKA: NASA.
- Context:
- It is an adaptive variant of the Mirror Descent Stochastic Approximation (MDSA).
- See: Stochastic Approximation Algorithm, Mirror Descent Stochastic Approximation----
References
2012
- (Ouyang & Gray, 2012) ⇒ Hua Ouyang, and Alexander Gray. (2012). “NASA: Achieving Lower Regrets and Faster Rates via Adaptive Stepsizes.” In: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2012). ISBN:978-1-4503-1462-6 doi:10.1145/2339530.2339557