Richard Bergna

According to our database, Richard Bergna authored at least 6 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Activation-Space Uncertainty Quantification for Pretrained Networks.

Richard Bergna, Stefan Depeweg, Sergio Calvo-Ordoñez, Jonathan Plenk, Álvaro Cartea, José Miguel Hernández-Lobato

CoRR, February, 2026

Richer Bayesian Last Layers with Subsampled NTK Features.

Sergio Calvo-Ordoñez, Jonathan Plenk, Richard Bergna, Álvaro Cartea, Yarin Gal, José Miguel Hernández-Lobato, Kamil Ciosek

CoRR, February, 2026

2025

Post-Hoc Uncertainty Quantification in Pre-Trained Neural Networks via Activation-Level Gaussian Processes.

Richard Bergna, Stefan Depeweg, Sergio Calvo-Ordoñez, Jonathan Plenk, Álvaro Cartea, José Miguel Hernández-Lobato

CoRR, February, 2025

Observation Noise and Initialization in Wide Neural Networks.

Sergio Calvo-Ordoñez, Jonathan Plenk, Richard Bergna, Álvaro Cartea, José Miguel Hernández-Lobato, Konstantina Palla, Kamil Ciosek

CoRR, February, 2025

Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations.

Richard Bergna, Sergio Calvo-Ordoñez, Felix L. Opolka, Pietro Lio, José Miguel Hernández-Lobato

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2023

Graph Neural Stochastic Differential Equations.

Richard Bergna, Felix L. Opolka, Pietro Liò, José Miguel Hernández-Lobato

CoRR, 2023