Country
Fast AutoAugment
Sungbin Lim, Ildoo Kim, Taesup Kim, Chiheon Kim, Sungwoong Kim
In this paper, we propose an efficient search method of augmentation policies, called Fast AutoAugment,motivatedbyBayesianDA[36].
Contextual Bandits with Cross-Learning
Santiago Balseiro, Negin Golrezaei, Mohammad Mahdian, Vahab Mirrokni, Jon Schneider
In the classical contextual bandits problem, in each roundt, a learner observes some contextc, chooses some actiona to perform, and receives some reward ra,t(c).
Bayesian Alignments of Warped Multi-Output Gaussian Processes
Markus Kaiser, Clemens Otte, Thomas Runkler, Carl Henrik Ek
Neural Information Processing Systems http://nips.cc/
AlternatingMirrorDescent forConstrainedMin-MaxGames
An instance of natural occurrences of such constraints is when mixed strategies are used, which correspond to a probability simplex constraint.
Alternating Mirror Descent for Constrained Min-Max Games
Notef = andg = are functions. Theorem 4.4 withrespecttok k1-norm; see Example A.3 in Section A.2.1.
ARegret-VarianceTrade-OffinOnlineLearning
Building on this result, we show several examples of how variance of predictions can be exploited in learning.
Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
Adil SALIM, Dmitry Koralev, Peter Richtarik
Neural Information Processing Systems http://nips.cc/