works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

cs.LG2026

Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus

Rasmus Tirsgaard, Laurits Fredsgaard, Marisa Wodrich +2

The paper proposes a semi-supervised learning approach for molecular graph data that uses an ensemble consensus objective to improve prediction accuracy, robustness, and calibratio…

cs.LG2026

Same Graph, Different Likelihoods: Calibration of Autoregressive Graph Generators via Permutation-Equivalent Encodings

Laurits Fredsgaard, Aaron Thomas, Michael Riis Andersen +2

Autoregressive graph generators define likelihoods via a sequential construction process, but these likelihoods are only meaningful if they are consistent across all linearizations…

cs.LG2026

Practical Deep Heteroskedastic Regression

Mikkel Jordahn, Jonas Vestergaard Jensen, James Harrison +2

Uncertainty quantification (UQ) in deep learning regression is of wide interest, as it supports critical applications including sequential decision making and risk-sensitive tasks.…

cs.LG2025

On Joint Regularization and Calibration in Deep Ensembles

Laurits Fredsgaard, Mikkel N. Schmidt

Deep ensembles are a powerful tool in machine learning, improving both model performance and uncertainty calibration. While ensembles are typically formed by training and tuning mo…

cs.LG2025

On Local Posterior Structure in Deep Ensembles

Mikkel Jordahn, Jonas Vestergaard Jensen, Mikkel N. Schmidt +1

Bayesian Neural Networks (BNNs) often improve model calibration and predictive uncertainty quantification compared to point estimators such as maximum-a-posteriori (MAP). Similarly…