Søren Hauberg

Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections AISTATS 2025 Geometric Contact Flows: Contactomorphisms for Dynamics and Control ICML 2025 Identifying Metric Structures of Deep Latent Variable Models ICML 2025 Riemann$^2$: Learning Riemannian Submanifolds from Riemannian Data AISTATS 2025 A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences NeurIPS 2024 Gradients of Functions of Large Matrices NeurIPS 2024 Improving Adversarial Energy-Based Model via Diffusion Process ICML 2024 Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification MICCAI 2024 Neural Contractive Dynamical Systems ICLR 2024 Reparameterization invariance in approximate Bayesian inference NeurIPS 2024 Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information NeurIPS 2024 Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval NeurIPS 2023 Learning to Taste: A Multimodal Wine Dataset NeurIPS 2023 On Masked Pre-training and the Marginal Likelihood NeurIPS 2023 Riemannian Laplace approximations for Bayesian neural networks NeurIPS 2023 Laplacian Autoencoders for Learning Stochastic Representations NeurIPS 2022 Probabilistic spatial transformer networks UAI 2022 Revisiting Active Sets for Gaussian Process Decoders NeurIPS 2022 Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval ICCV 2021 Bounds all around: training energy-based models with bidirectional bounds NeurIPS 2021 Hierarchical VAEs Know What They Don’t Know ICML 2021 Learning Riemannian Manifolds for Geodesic Motion Skills RSS 2021 Explicit Disentanglement of Appearance and Perspective in Generative Models NeurIPS 2019 Probabilistic Riemannian submanifold learning with wrapped Gaussian process latent variable models AISTATS 2019 Reliable training and estimation of variance networks NeurIPS 2019 Deep Diffeomorphic Transformer Networks CVPR 2018 Latent Space Oddity: on the Curvature of Deep Generative Models ICLR 2018 A Locally Adaptive Normal Distribution NeurIPS 2016 Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation AISTATS 2016 Open Problem: Kernel methods on manifolds and metric spaces. What is the probability of a positive definite geodesic exponential kernel? COLT 2016 Probabilistic Solutions to Differential Equations and their Application to Riemannian Statistics AISTATS 2014 A Geometric take on Metric Learning NeurIPS 2012