13 citations · 30 across the 16 of their papers we have counts for
17 papers
Matrix-Free Least Squares Solvers: Values, Gradients, and What to Do With Them
Hrittik Roy, Søren Hauberg, Nicholas Krämer
This paper argues that the method of least squares has significant unfulfilled potential in modern machine learning, far beyond merely being a tool for fitting linear models. To re…
Bayesian generative models can flag performance loss, bias, and out-of-distribution image content
Miguel López-Pérez, Marco Miani, Valery Naranjo +2
Generative models are popular for medical imaging tasks such as anomaly detection, feature extraction, data visualization, or image generation. Since they are parameterized by deep…
Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
Marco Miani, Lorenzo Beretta, Søren Hauberg
Current uncertainty quantification is memory and compute expensive, which hinders practical uptake. To counter, we develop Sketched Lanczos Uncertainty (SLU): an architecture-agnos…
Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections
Marco Miani, Hrittik Roy, Søren Hauberg
Bayesian deep learning all too often underfits so that the Bayesian prediction is less accurate than a simple point estimate. Uncertainty quantification then comes at the cost of a…
Decoder ensembling for learned latent geometries
Stas Syrota, Pablo Moreno-Muñoz, Søren Hauberg
Latent space geometry provides a rigorous and empirically valuable framework for interacting with the latent variables of deep generative models. This approach reinterprets Euclide…
Reparameterization invariance in approximate Bayesian inference
Hrittik Roy, Marco Miani, Carl Henrik Ek +4
Current approximate posteriors in Bayesian neural networks (BNNs) exhibit a crucial limitation: they fail to maintain invariance under reparameterization, i.e. BNNs assign differen…
Gradients of Functions of Large Matrices
Nicholas Krämer, Pablo Moreno-Muñoz, Hrittik Roy +1
Tuning scientific and probabilistic machine learning models for example, partial differential equations, Gaussian processes, or Bayesian neural networks often relies on eva…
Learning to Taste: A Multimodal Wine Dataset
Thoranna Bender, Simon Moe Sørensen, Alireza Kashani +5
We present WineSensed, a large multimodal wine dataset for studying the relations between visual perception, language, and flavor. The dataset encompasses 897k images of wine label…
On Masked Pre-training and the Marginal Likelihood
Pablo Moreno-Muñoz, Pol G. Recasens, Søren Hauberg
Masked pre-training removes random input dimensions and learns a model that can predict the missing values. Empirical results indicate that this intuitive form of self-supervised l…
Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification
Kilian Zepf, Selma Wanna, Marco Miani +5
Image segmentation relies heavily on neural networks which are known to be overconfident, especially when making predictions on out-of-distribution (OOD) images. This is a common s…
Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval
Frederik Warburg, Marco Miani, Silas Brack +1
We propose the first Bayesian encoder for metric learning. Rather than relying on neural amortization as done in prior works, we learn a distribution over the network weights with…
Revisiting Active Sets for Gaussian Process Decoders
Pablo Moreno-Muñoz, Cilie W Feldager, Søren Hauberg
Decoders built on Gaussian processes (GPs) are enticing due to the marginalisation over the non-linear function space. Such models (also known as GP-LVMs) are often expensive and n…
Laplacian Autoencoders for Learning Stochastic Representations
Marco Miani, Frederik Warburg, Pablo Moreno-Muñoz +2
Established methods for unsupervised representation learning such as variational autoencoders produce none or poorly calibrated uncertainty estimates making it difficult to evaluat…
Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization
Andrea Vallone, Frederik Warburg, Hans Hansen +2
Place recognition and visual localization are particularly challenging in wide baseline configurations. In this paper, we contribute with the \emph{Danish Airs and Grounds} (DAG) d…
Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval
Frederik Warburg, Martin Jørgensen, Javier Civera +1
Uncertainty quantification in image retrieval is crucial for downstream decisions, yet it remains a challenging and largely unexplored problem. Current methods for estimating uncer…
Probabilistic Spatial Transformer Networks
Pola Schwöbel, Frederik Warburg, Martin Jørgensen +2
Spatial Transformer Networks (STNs) estimate image transformations that can improve downstream tasks by `zooming in' on relevant regions in an image. However, STNs are hard to trai…
Reliable training and estimation of variance networks
Nicki S. Detlefsen, Martin Jørgensen, Søren Hauberg
We propose and investigate new complementary methodologies for estimating predictive variance networks in regression neural networks. We derive a locally aware mini-batching scheme…