activity
20182021
most citedMulti-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation

8 citations · 14 across the 3 of their papers we have counts for

collaborators

8 papers

cs.LG20215 cited

On Stein Variational Neural Network Ensembles

Francesco D'Angelo, Vincent Fortuin, Florian Wenzel

Ensembles of deep neural networks have achieved great success recently, but they do not offer a proper Bayesian justification. Moreover, while they allow for averaging of predictio…

cs.LG2020

Hyperparameter Ensembles for Robustness and Uncertainty Quantification

Florian Wenzel, Jasper Snoek, Dustin Tran +1

Ensembles over neural network weights trained from different random initialization, known as deep ensembles, achieve state-of-the-art accuracy and calibration. The recently introdu…

stat.ML20201 cited

Automated Augmented Conjugate Inference for Non-conjugate Gaussian Process Models

Théo Galy-Fajou, Florian Wenzel, Manfred Opper

We propose automated augmented conjugate inference, a new inference method for non-conjugate Gaussian processes (GP) models. Our method automatically constructs an auxiliary variab…

stat.ML2020

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

Florian Wenzel, Kevin Roth, Bastiaan S. Veeling +7

During the past five years the Bayesian deep learning community has developed increasingly accurate and efficient approximate inference procedures that allow for Bayesian inference…

stat.ML20198 cited

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

Théo Galy-Fajou, Florian Wenzel, Christian Donner +1

We propose a new scalable multi-class Gaussian process classification approach building on a novel modified softmax likelihood function. The new likelihood has two benefits: it lea…

stat.ML2018

Quasi-Monte Carlo Variational Inference

Alexander Buchholz, Florian Wenzel, Stephan Mandt

Many machine learning problems involve Monte Carlo gradient estimators. As a prominent example, we focus on Monte Carlo variational inference (MCVI) in this paper. The performance…