Gianluca Detommaso
Gianluca Detommaso
Applied Scientist, AWS
Verified email at - Homepage
Cited by
Cited by
A Stein variational Newton method
G Detommaso, T Cui, A Spantini, Y Marzouk, R Scheichl
NeurIPS 2018, 2018
HINT: Hierarchical Invertible Neural Transport for Density Estimation and Bayesian Inference
J Kruse, G Detommaso, R Scheichl, U Köthe
AAAI-21, 2019
Continuous level Monte Carlo and sample-adaptive model hierarchies
G Detommaso, T Dodwell, R Scheichl
SIAM/ASA Journal on Uncertainty Quantification 7 (1), 93-116, 2019
Multilevel dimension-independent likelihood-informed MCMC for large-scale inverse problems
T Cui, G Detommaso, R Scheichl
arXiv preprint arXiv:1910.12431, 2019
A data-centric approach to generative modelling for 3D-printed steel
TJ Dodwell, LR Fleming, C Buchanan, P Kyvelou, G Detommaso, ...
Proceedings of the Royal Society A 477 (2255), 20210444, 2021
Stein variational online changepoint detection with applications to Hawkes processes and neural networks
G Detommaso, H Hoitzing, T Cui, A Alamir
ICML 2019 (Workshop), 2019
Fortuna: A Library for Uncertainty Quantification in Deep Learning
G Detommaso, A Gasparin, M Donini, M Seeger, AG Wilson, ...
arXiv preprint arXiv:2302.04019, 2023
Causal Bias Quantification for Continuous Treatments
G Detommaso, M Brückner, P Schulz, V Chernozhukov
arXiv preprint arXiv:2106.09762, 2021
Explaining Multiclass Classifiers with Categorical Values: A Case Study in Radiography
L Franceschi, C Zor, MB Zafar, G Detommaso, C Archambeau, T Madl, ...
ICLR 2023 Workshop on Trustworthy Machine Learning for Healthcare, 2023
Uncertainty Calibration in Bayesian Neural Networks via Distance-Aware Priors
G Detommaso, A Gasparin, A Wilson, C Archambeau
arXiv preprint arXiv:2207.08200, 2022
The system can't perform the operation now. Try again later.
Articles 1–10