8 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…
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…
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…
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…
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…