Fetching the paper…
Reading the bibliography…
We present an algorithm for the statistical learning setting with a bounded exp-concave loss in $d$ dimensions that obtains excess risk $O(d \log(1/\delta)/n)$ with probability at least $1 - \delta$.
On tail probabilities for martingales
David A. Freedman · 1975
Earlier work this paper cites.
Entropy, compactness, and the approximation of operators , volume 98
Bernd Carl and Irmtraud Stephani · 1990
Earlier work this paper cites.
The strength of weak learnability
Robert E. Schapire · 1990
Earlier work this paper cites.
Aggregating strategies
Volodimir G Vovk · 1990
Earlier work this paper cites.
An introduction to computational learning theory
Michael J. Kearns and Umesh Vazirani · 1994
Earlier work this paper cites.
The nature of statistical learning theory
Vladimir N. Vapnik · 1995
Earlier work this paper cites.
Robustly minimax codes for universal data compression’, the 21’st
Jun-ichi Takeuchi and Andrew R Barron · 1998
Earlier work this paper cites.
Averaging expert predictions
Jyrki Kivinen and Manfred K Warmuth · 1999
Earlier work this paper cites.
On the generalization ability of on-line learning algorithms
Nicolò Cesa-Bianchi, Alex Conconi, and Claudio Gentile · 2001
Earlier work this paper cites.
Stability and generalization
Olivier Bousquet and André Elisseeff · 2002
Earlier work this paper cites.
Learning and Generalization with Applications to Neural Networks
Mathukumalli Vidyasagar · 2002
Cited alongside, same era.
Logarithmic regret algorithms for online convex optimization
Elad Hazan, Amit Agarwal, and Satyen Kale · 2007
Cited alongside, same era.
Progressive mixture rules are deviation suboptimal
Jean-Yves Audibert · 2008
Cited alongside, same era.
Learning by mirror averaging
Anatoli Juditsky, Philippe Rigollet, and Alexandre B Tsybakov · 2008
Cited alongside, same era.
Fast learning rates in statistical inference through aggregation
Jean-Yves Audibert · 2009
Cited alongside, same era.
On the generalization ability of online strongly convex programming algorithms
Sham M. Kakade and Ambuj Tewari · 2009
Cited alongside, same era.
Mixability in statistical learning
Tim van Erven, Peter Grünwald, Mark D. Reid, and Robert C. Williamson · 2012
Later among the works it cites.
Open problem: Fast stochastic exp-concave optimization
Tomer Koren · 2013
Later among the works it cites.
Optimal learning with q-aggregation
Guillaume Lecué and Philippe Rigollet · 2014
Later among the works it cites.
Excess risk bounds for exponentially concave losses
Mehrdad Mahdavi and Rong Jin · 2014
Later among the works it cites.
From stochastic mixability to fast rates
Nishant A. Mehta and Robert C. Williamson · 2014
Later among the works it cites.
Fast rates for exp-concave empirical risk minimization
Tomer Koren and Kfir Levy · 2015
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Aggregation via empirical risk minimization
Guillaume Lecué and Shahar Mendelson · 2009
Cited alongside, same era.
Fast rates for regularized objectives
Karthik Sridharan, Shai Shalev-Shwartz, and Nathan Srebro · 2009
Cited alongside, same era.
The safe bayesian
Peter Grünwald · 2012
Cited alongside, same era.
Beyond logarithmic bounds in online learning
Francesco Orabona, Nicolo Cesa-Bianchi, and Claudio Gentile · 2012
Cited alongside, same era.
Lower and upper bounds on the generalization of stochastic exponentially concave optimization
Mehrdad Mahdavi, Lijun Zhang, and Rong Jin · 2015
Later among the works it cites.
Fast rates in statistical and online learning
Tim van Erven, Peter D. Grünwald, Nishant A. Mehta, Mark D. Reid, and Robert C. Williamson · 2015
Later among the works it cites.
Tightening the sample complexity of empirical risk minimization via preconditioned stability
Alon Gonen and Shai Shalev-Shwartz · 2016
Closest in time.