research
∙
07/18/2023
Batched Predictors Generalize within Distribution
We study the generalization properties of batched predictors, i.e., mode...
share
research
∙
02/27/2023
Detecting and Mitigating Mode-Collapse for Flow-based Sampling of Lattice Field Theories
We study the consequences of mode-collapse of normalizing flows in the c...
research
∙
07/17/2022
Gradients should stay on Path: Better Estimators of the Reverse- and Forward KL Divergence for Normalizing Flows
We propose an algorithm to estimate the path-gradient of both the revers...
research
∙
06/17/2022
Path-Gradient Estimators for Continuous Normalizing Flows
Recent work has established a path-gradient estimator for simple variati...
research
∙
06/10/2022
Diffeomorphic Counterfactuals with Generative Models
Counterfactuals can explain classification decisions of neural networks ...
research
∙
11/22/2021
Machine Learning of Thermodynamic Observables in the Presence of Mode Collapse
Estimating the free energy, as well as other thermodynamic observables, ...
research
∙
08/23/2021
Deep learning for surrogate modelling of 2D mantle convection
Traditionally, 1D models based on scaling laws have been used to paramet...
research
∙
12/18/2020
Towards Robust Explanations for Deep Neural Networks
Explanation methods shed light on the decision process of black-box clas...
research
∙
07/20/2020
Fairwashing Explanations with Off-Manifold Detergent
Explanation methods promise to make black-box classifiers more transpare...
research
∙
07/14/2020
On Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
In this work, we demonstrate that applying deep generative machine learn...
research
∙
10/29/2019
Asymptotically Unbiased Generative Neural Sampling
We propose a general framework for the estimation of observables with ge...
research
∙
06/19/2019
Explanations can be manipulated and geometry is to blame
Explanation methods aim to make neural networks more trustworthy and int...
research
∙
03/26/2019
Comment on "Solving Statistical Mechanics Using VANs": Introducing saVANt - VANs Enhanced by Importance and MCMC Sampling
In this comment on "Solving Statistical Mechanics Using Variational Auto...
research
∙
10/23/2018