Online Learning under Delayed Feedback

Stochastic Processes

Doob, Joseph L · 1953

Earlier work this paper cites.

Probability inequalities for sums of bounded random variables

Hoeffding, Wassily · 1963

Earlier work this paper cites.

The Theory of the Riemann Zeta-Functions

Titchmarsh, Edward Charles and Heath-Brown, David Rodney · 1987

Earlier work this paper cites.

Finite-time analysis of the multiarmed bandit problem

Auer, Peter, Cesa-Bianchi, Nicolò, and Fischer, Paul · 2002

Earlier work this paper cites.

On delayed prediction of individual sequences

Weinberger, Marcelo J. and Ordentlich, Erik · 2002

Earlier work this paper cites.

On-line learning with delayed label feedback

Mesterharm, Chris J · 2005

Cited alongside, same era.

Prediction, Learning, and Games

Cesa-Bianchi, Nicolò and Lugosi, Gábor · 2006

Cited alongside, same era.

Improving on-line learning

Mesterharm, Chris J · 2007

Cited alongside, same era.

Slow learners are fast

Langford, John, Smola, Alexander, and Zinkevich, Martin · 2009

Cited alongside, same era.

A contextual-bandit approach to personalized news article recommendation

Li, Lihong, Chu, Wei, Langford, John, and Schapire, Robert E · 2010

Cited alongside, same era.

Online markov decision processes under bandit feedback

Neu, Gergely, György, András, Szepesvári, Csaba, and Antos, András · 2010

Later among the works it cites.

Distributed delayed stochastic optimization

Agarwal, Alekh and Duchi, John · 2011

Later among the works it cites.

Efficient optimal learning for contextual bandits

Dudik, Miroslav, Hsu, Daniel, Kale, Satyen, Karampatziakis, Nikos, Langford, John, Reyzin, Lev, and Zhang, Tong · 2011

Later among the works it cites.

The KL-UCB algorithm for bounded stochastic bandits and beyond

Garivier, Aurélien and Cappé, Olivier · 2011

Later among the works it cites.

Parallelizing exploration-exploitation tradeoffs with gaussian process bandit optimization

Desautels, Thomas, Krause, Andreas, and Burdick, Joel · 2012

Later among the works it cites.