Florian Wenzel

is this you? claim profile

0 followers
Humboldt-Universität zu Berlin

Bayesian Neural Network Priors Revisited

Isotropic Gaussian priors are the de facto standard for modern Bayesian ...
02/12/2021 ∙ by Vincent Fortuin, et al. ∙ 16 ∙ share

read it
Hyperparameter Ensembles for Robustness and Uncertainty Quantification

Ensembles over neural network weights trained from different random init...
06/24/2020 ∙ by Florian Wenzel, et al. ∙ 13 ∙ share

read it
Automated Augmented Conjugate Inference for Non-conjugate Gaussian Process Models

We propose automated augmented conjugate inference, a new inference meth...
02/26/2020 ∙ by Theo Galy-Fajou, et al. ∙ 0 ∙ share

read it
How Good is the Bayes Posterior in Deep Neural Networks Really?

During the past five years the Bayesian deep learning community has deve...
02/06/2020 ∙ by Florian Wenzel, et al. ∙ 27 ∙ share

read it
Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation

We propose a new scalable multi-class Gaussian process classification ap...
05/23/2019 ∙ by Theo Galy-Fajou, et al. ∙ 6 ∙ share

read it
Quasi-Monte Carlo Variational Inference

Many machine learning problems involve Monte Carlo gradient estimators. ...
07/04/2018 ∙ by Alexander Buchholz, et al. ∙ 0 ∙ share

read it
Scalable Generalized Dynamic Topic Models

Dynamic topic models (DTMs) model the evolution of prevalent themes in l...
03/21/2018 ∙ by Patrick Jähnichen, et al. ∙ 0 ∙ share

read it
Efficient Gaussian Process Classification Using Polya-Gamma Data Augmentation

We propose an efficient stochastic variational approach to GP classifica...
02/18/2018 ∙ by Florian Wenzel, et al. ∙ 0 ∙ share

read it
Bayesian Nonlinear Support Vector Machines for Big Data

We propose a fast inference method for Bayesian nonlinear support vector...
07/18/2017 ∙ by Florian Wenzel, et al. ∙ 0 ∙ share

read it

Florian Wenzel

Featured Co-authors

Stephan Mandt

Dustin Tran

Gunnar Rätsch

Sebastian Nowozin

Jasper Snoek

Mark van der Wilk

Manfred Opper

Rodolphe Jenatton

Marius Kloft

Tim Salimans

Vincent Fortuin

Bayesian Neural Network Priors Revisited

Hyperparameter Ensembles for Robustness and Uncertainty Quantification

Automated Augmented Conjugate Inference for Non-conjugate Gaussian Process Models

How Good is the Bayes Posterior in Deep Neural Networks Really?

Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation

Quasi-Monte Carlo Variational Inference

Scalable Generalized Dynamic Topic Models

Efficient Gaussian Process Classification Using Polya-Gamma Data Augmentation

Bayesian Nonlinear Support Vector Machines for Big Data