A Closer Look at Adaptive Regret

By Dmitry Adamskiy, Wouter M. Koolen, Alexey V. Chernov, Vladimir G Vovk. 2012

101 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.

1. Tianbao Yang
2. Zhi-Hua Zhou
3. Jakub Konecný
4. Wendi Wu
5. Lijun Zhang
6. Rong Jin
7. Csaba Szepesvari
8. Peilin Zhao

Citations in the corpus

• Decentralized Online Learning: Take Benefits from Others’ Data without Sharing Your Own to Track Global Trend (2019, methodology): “, 2015], decentralized online gradient descent [Akbari et al., 2017], decentralized continuous-time online saddle-point method [Lee et al., 2016], decentralized online Nesterov’s primal-dual method [Nedić et al., 2015, Lee et al., 2018], and online distributed dual averaging [Hosseini et al., 2013].”
• Shifting Regret, Mirror Descent, and Matrices (2016, background): “Another measure introduced by Hazan & Seshadhri (2009) considers regret over contiguous time intervals, called the adaptive regret, while recently a stronger version of the same concept was introduced by Daniely et al. (2015) (see, also, Adamskiy et al. 2012).”
• Competing with Automata-based Expert Sequences (2018, methodology): “, 2015, Adamskiy et al., 2012]. Remarkably, it was shown by Adamskiy et al. [2012] that the algorithm designed by Herbster and Warmuth [1998] is also optimal for adaptive regret.”
• Online Convex Optimization in Dynamic Environments (2015, background): “2) to decrease to zero as the algorithm runs [33], [34].”
• Dynamic Regret of Strongly Adaptive Methods (2017, background): “In the setting of “prediction with expert advice”, Adamskiy et al. (2012) have shown that the tracking regret can be derived from the adaptive regret.”
• Online Optimization in Dynamic Environments (2013, background): “2) to decrease to zero as the algorithm runs [32,33].”