Europe
Variational Bayesian Decision-making for Continuous Utilities
Tomasz Kuśmierczyk, Joseph Sakaya, Arto Klami
Bayesian decision theory outlines arigorous framework for making optimal decisions based on maximizing expected utility over a model posterior.
5b84864ff8474fd742c66f219b2eaac1-Supplemental-Conference.pdf
Images taken between 2013 and 2015 are used as the validation set.
Scalable Hyperparameter Transfer Learning
Valerio Perrone, Rodolphe Jenatton, Matthias W. Seeger, Cedric Archambeau
In this work, we aim to warm-start BO in the context of hyperparameter optimization (HPO).
Deep, complex, invertible networks for inversion of transmission effects in multimode optical fibres
Oisín Moran, Piergiorgio Caramazza, Daniele Faccio, Roderick Murray-Smith
The experimental data is used to train complex-weighted models with a range of regularisation approaches.
Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem
Gonzalo Mena, Jonathan Niles-Weed
These results give the first characterization of the large-sample behavior of entropic OT for unbounded probability measures in arbitrary dimension.
db6461eaf0eaeaad1d9c4a70e4818cbd-Supplemental-Conference.pdf
Weshowaseparation result: on one hand, if the query radiusλis strictly smaller than the adversary's perturbation budgetρ, then distribution-free robust learning is impossible for a widevarietyofconcept classes; ontheotherhand,thesettingλ=ρallowsusto develop robust ERM algorithms.
CatBoost: unbiased boosting with categorical features
Liudmila Prokhorenkova, Gleb Gusev, Aleksandr Vorobev, Anna Veronika Dorogush, Andrey Gulin
We show in this paper that all existing implementations of gradient boosting face the following statistical issue.
