Filters








3 Hits in 5.7 sec

Practical Contextual Bandits with Regression Oracles [article]

Dylan J. Foster, Alekh Agarwal, Miroslav Dudík, Haipeng Luo, Robert E. Schapire
2018 arXiv   pre-print
Our approach generalizes both UCB and LinUCB to far more expressive possible model classes and achieves low regret under certain distributional assumptions.  ...  Our algorithms leverage the availability of a regression oracle for the value-function class, a more realistic and reasonable oracle than the classification oracles over policies typically assumed by agnostic  ...  Note that RegCB is not minimax optimal: while it can obtain O KT log F regret or even logarithmic regret under certain distributional assumptions, which we describe shortly, for some instances it can make  ... 
arXiv:1803.01088v1 fatcat:f2nmxg3izvbifhr3m2fg72uftu

On Fitting Finite Dirichlet Mixture Using ECM and MML [chapter]

Nizar Bouguila, Djemel Ziou
2005 Lecture Notes in Computer Science  
dimensional distributions Regular vines are a graphical tool for representing complex high dimensional distributions as bivariate and conditional bivariate distributions.  ...  for high-dimensional classification.  ...  Most studies, however, are rather focused on the cases with the single dimensional (or at least low dimensional) function parameter in the regression model since the dimensionality costs higher order smoothness  ... 
doi:10.1007/11551188_19 fatcat:gtzi5u6emvfyxea3zbklobnvom

Conference Program and Book of Abstracts 13th International Conference on Stochastic Programming Organising Committee Advisory Program Committee Scientific Committee WELCOME FROM THE CHAIR

Marida Bertocchi -Chair, Giorgio Consigli, Moriggia Vittorio, Ortobelli Sergio, Rosella Lozza, Giacometti, Teresa Maria, Vespucci, Francesca Maggioni, Paolo Pisciella, Stefano Zigrino, Sebastiano Vitali (+42 others)
unpublished
Often times, these models result in stochastic programs with high-dimensional recourse vectors.  ...  In the application section, the proposed approach is compared with traditional neural networks in terms of their performance against the complex problems Anton J.  ...  This prospective is used for example in deciding which capacity we need to expand over the next years.  ... 
fatcat:b2q6nnj52nbudkna2lpsjmhtlq