A Note on the Unification of Adaptive Online Learning
Sign Up to like & getrecommendations! Published in 2017 at "IEEE Transactions on Neural Networks and Learning Systems"
DOI: 10.1109/tnnls.2016.2527053
Abstract: In online convex optimization, adaptive algorithms, which can utilize the second-order information of the loss function’s (sub)gradient, have shown improvements over standard gradient methods. This paper presents a framework Follow the Bregman Divergence Leader that… read more here.
Keywords: note unification; adaptive online; online learning; online ... See more keywords