Competing with Automata-based Expert Sequences

9 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Decentralized Online Learning: Take Benefits from Others’ Data without Sharing Your Own to Track Global Trend (2019, background): “…is usually termed as shifting regret or tracking regret [Herbster and Warmuth, 1998, Gy¨orgy et al., 2005, Gyorgy et al., 2012, Gy¨orgy and Szepesv´ari, 2016, Mourtada and Maillard, 2017, Adamskiy et al., 2016, Wei et al., 2016, Cesa-Bianchi et al., 2012, Mohri and Yang, 2018, Jun et al., 2017].”
Proximal Online Gradient Is Optimum for Dynamic Regret: A General Lower Bound (2021, background): “Shifting regret (or tracking regret) The M−shifting regret of an algorithm A ∈ A is defined by [6], [38], [40]–[47]”
Proximal Online Gradient is Optimum for Dynamic Regret (2018, background): “ires the smoothness of ft. Our proposed online methods does not have those limitations. C. Shifting regret (or tracking regret) The M−shifting regret of an algorithm A∈ A is deﬁned by [6], [38], [40]–[47] ReA T := XT t=1 f t(x) − min {yt}T t=1∈L T M XT t=1 f(y), (8) where LT M = n {yt}T t=1 : PT−1 t”