Gianluca Detommaso

According to our database, Gianluca Detommaso authored at least 14 papers between 2018 and 2024.

Collaborative distances:

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

2024

Fortuna: A Library for Uncertainty Quantification in Deep Learning.

Gianluca Detommaso, Alberto Gasparin, Michele Donini, Matthias W. Seeger, Andrew Gordon Wilson, Cédric Archambeau

J. Mach. Learn. Res., 2024

Cost-Effective Hallucination Detection for LLMs.

Simon Valentin, Jinmiao Fu, Gianluca Detommaso, Shaoyuan Xu, Giovanni Zappella, Bryan Wang

CoRR, 2024

Multicalibration for Confidence Scoring in LLMs.

Gianluca Detommaso, Martín Bertrán, Riccardo Fogliato, Aaron Roth

CoRR, 2024

Multicalibration for Confidence Scoring in LLMs.

Gianluca Detommaso, Martin Bertran Lopez, Riccardo Fogliato, Aaron Roth

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Distance-aware Calibration for Pre-trained Language Models.

Alberto Gasparin, Gianluca Detommaso

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023

Explaining Multiclass Classifiers with Categorical Values: A Case Study in Radiography.

Luca Franceschi, Cemre Zor, Muhammad Bilal Zafar, Gianluca Detommaso, Cédric Archambeau, Tamas Madl, Michele Donini, Matthias W. Seeger

Proceedings of the Trustworthy Machine Learning for Healthcare, 2023

2022

Uncertainty Calibration in Bayesian Neural Networks via Distance-Aware Priors.

Gianluca Detommaso, Alberto Gasparin, Andrew Wilson, Cédric Archambeau

CoRR, 2022

2021

Causal Bias Quantification for Continuous Treatment.

Gianluca Detommaso, Michael Brückner, Philip Schulz, Victor Chernozhukov

CoRR, 2021

HINT: Hierarchical Invertible Neural Transport for Density Estimation and Bayesian Inference.

Jakob Kruse, Gianluca Detommaso, Ullrich Köthe, Robert Scheichl

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2019

Continuous Level Monte Carlo and Sample-Adaptive Model Hierarchies.

Gianluca Detommaso, Tim J. Dodwell, Robert Scheichl

SIAM/ASA J. Uncertain. Quantification, 2019

Multilevel Dimension-Independent Likelihood-Informed MCMC for Large-Scale Inverse Problems.

Tiangang Cui, Gianluca Detommaso, Robert Scheichl

CoRR, 2019

HINT: Hierarchical Invertible Neural Transport for General and Sequential Bayesian inference.

Gianluca Detommaso, Jakob Kruse, Lynton Ardizzone, Carsten Rother, Ullrich Köthe, Robert Scheichl

CoRR, 2019

Stein Variational Online Changepoint Detection with Applications to Hawkes Processes and Neural Networks.

Gianluca Detommaso, Hanne Hoitzing, Tiangang Cui, Ardavan Alamir

CoRR, 2019

2018

A Stein variational Newton method.

Gianluca Detommaso, Tiangang Cui, Youssef M. Marzouk, Alessio Spantini, Robert Scheichl

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018