F. Wenzel

发表

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

Sebastian Nowozin, Stephan Mandt, Jasper Snoek, 2020, ICML.

Hyperparameter Ensembles for Robustness and Uncertainty Quantification pdf

Jasper Snoek, Dustin Tran, Florian Wenzel, 2020, NeurIPS.

The Natural Neural Tangent Kernel: Neural Network Training Dynamics under Natural Gradient Descent

Tim G. J. Rudner, F. Wenzel, 2019 .

Distilling Ensembles Improves Uncertainty Estimates

Dustin Tran, Florian Wenzel, Rodolphe Jenatton, 2020 .

Quasi-Monte Carlo Flows

F. Wenzel, S. Mandt, A. Buchholz, 2018, EasyChair Preprints.

EasyChair Preprint No 684 Quasi-Monte Carlo Flows

F. Wenzel, S. Mandt, A. Buchholz, 2022 .

Scalable Approximate Inference for the Bayesian Nonlinear Support Vector Machine

M. Kloft, F. Wenzel, M. Deutsch, 2016 .

Generalizing and Scaling up Dynamic Topic Models via Inducing Point Variational Inference

F. Wenzel, P. Jähnichen, 2017 .

Assaying Out-Of-Distribution Generalization in Transfer Learning

B. Schiele, T. Brox, F. Wenzel, 2022, ArXiv.

Fast Inference in Non-Conjugate Gaussian Process Models via Data Augmentation

F. Wenzel, Théo Galy-Fajou, Christian Donner, 2018 .

Deep Classifiers with Label Noise Modeling and Distance Awareness

F. Wenzel, Rodolphe Jenatton, Dustin Tran, 2021, Trans. Mach. Learn. Res..

Assaying Out-Of-Distribution Generalization in Transfer Learning

B. Schiele, B. Schölkopf, T. Brox, 2022, NeurIPS.

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

Bastiaan S. Veeling, Tim Salimans, F. Wenzel, 2020, ICML.

Bayesian Neural Network Priors Revisited

Richard E. Turner, Mark van der Wilk, Gunnar Rätsch, 2021, ICLR.

Sparse probit linear mixed model

Shinichi Nakajima, Marius Kloft, John P. Cunningham, 2015, Machine Learning.

Sparse Estimation in a Correlated Probit Model

J. Cunningham, M. Kloft, F. Wenzel, 2015, ArXiv.

Are Multimodal Models Robust to Image and Text Perturbations?

F. Wenzel, Bo Li, Mu Li, 2022, ArXiv.

Leveraging sparse and shared feature activations for disentangled representation learning

F. Wenzel, B. Scholkopf, A. Achille, 2023, 2304.07939.

Leveraging sparse and shared feature activations for disentangled representation learning

B. Schölkopf, F. Wenzel, B. Scholkopf, 2023, NeurIPS.

A data augmentation perspective on diffusion models and retrieval

Max F. Burg, F. Wenzel, Chris Russell, 2023, ArXiv.

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning

Michael W. Dusenberry, Tim G. J. Rudner, Angelos Filos, 2021, ArXiv.

Scalable Generalized Dynamic Topic Models pdf

Patrick Jähnichen, Marius Kloft, Stephan Mandt, 2018, AISTATS.

Efficient Gaussian Process Classification Using Polya-Gamma Data Augmentation pdf

Marius Kloft, Florian Wenzel, Manfred Opper, 2018, AAAI.

Bayesian Nonlinear Support Vector Machines for Big Data pdf

Marius Kloft, Florian Wenzel, Théo Galy-Fajou, 2017, ECML/PKDD.

On Stein Variational Neural Network Ensembles pdf

Florian Wenzel, Vincent Fortuin, Francesco D'Angelo, 2021, ArXiv.

Quasi-Monte Carlo Variational Inference

Stephan Mandt, Florian Wenzel, Alexander Buchholz, 2018, ICML.

Sparse MoEs meet Efficient Ensembles

Carlos Riquelme Ruiz, F. Wenzel, Jasper Snoek, 2021, Trans. Mach. Learn. Res..

Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries

F. Wenzel, Akash Srivastava, Kai Xu, 2023, ICML.

Separating Sparse Signals from Correlated Noise in Binary Classification

Shinichi Nakajima, Marius Kloft, Stephan Mandt, 2016, CFA@UAI.

Scalable Inference in Dynamic Mixture Models

M. Kloft, F. Wenzel, P. Jähnichen, 2016 .

Evaluating the Fairness of Discriminative Foundation Models in Computer Vision

F. Wenzel, V. Cevher, Chris Russell, 2023, AIES.

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

Florian Wenzel, Manfred Opper, Christian Donner, 2019, UAI.

Automated Augmented Conjugate Inference for Non-conjugate Gaussian Process Models

Florian Wenzel, Manfred Opper, Th'eo Galy-Fajou, 2020, AISTATS.

On the Challenges and Opportunities in Generative AI

Guy Van den Broeck, F. Wenzel, Robert Bamler, 2024, 2403.00025.

Image retrieval outperforms diffusion models on data augmentation

Max F. Burg, F. Wenzel, Chris Russell, 2023, 2304.10253.

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

Bastiaan S. Veeling, Tim Salimans, F. Wenzel, 2020 .

Finding Sparse Features in Strongly Confounded Medical Binary Data

J. Cunningham, M. Kloft, S. Nakajima, 2015 .