Andrea Pugnana

Andrea Pugnana

Hello there, this is Andrea!

I am a postdoc at University of Pisa, working on AI systems that know what they do not know.

Paper accepted at AISTATS 2025

Jan 22, 2025

The work “A Causal Framework for Evaluating Deferring Systems” (link to camera-ready version will be added asap) with Filippo Palomba, José M. Alvarez and Salvatore Ruggieri has been accepted at the The 28th International Conference on Artificial Intelligence and Statistics (AISTATS).

Paper accepted at the Senior-Member Track AAAI 2025

Dec 3, 2024

The work “Things Machine Learning Models know that they don’t know” (link to be added asap) with Salvatore Ruggieri has been accepted at the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI) 2025.

Paper accepted for DMLR publication

Sep 1, 2024

The work “Deep Neural Network Benchmarks for Selective Classification” has been accepted for pubblication in The Journal of Data-Centric Machine-Learning Research (DMLR).

Paper accepted at ECML-PKDD 2024

May 27, 2024

The work “Interpretable and Fair Mechanisms for Abstaining Classifiers” has been accepted at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) 2024.

PhD defended

May 24, 2024

I successfully defended my PhD thesis entitled “Topics in Selective Prediction”. A huge thanks to my PhD advisors, Salvatore Ruggieri and Francesca Chiaromonte for their guidance and support.

Presenting Topics in Selective Classification

Feb 7, 2023

I will present my work “Topics in Selective Classification” at AAAI 2023 Doctoral Consortium. The work summarizes my PhD project on selective classification, a machine learning paradigm that aims to improve the performance of classifiers by abstaining on difficult instances.

Paper accepted at AISTATS 2023

Jan 20, 2023

The work AUC-based Selective Classification has been accepted at the International Conference on Artificial Intelligence and Statistics (AISTATS) 2023. A huge thanks to my PhD supervisor Salvatore Ruggieri for his help. The work proposes a new selective classification method based on the Area Under the ROC Curve (AUC) metric. The method is model-agnostic and can be used with any classifier. See you in Valencia for the conference!

Paper accepted at AAAI Main Track 2023

Nov 19, 2022

The work A Model-agnostic Heuristics for Selective Classification has been accepted at the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI) 2023. A huge thanks to my PhD supervisor Salvatore Ruggieri for his help.

Paper accepted at the Senior-Member Track AAAI 2023

Oct 14, 2022

The work Can we Trust Fair AI? by Salvatore Ruggieri, José M. Alvarez, me, Laura State and Franco Turini has been accepted at the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI) 2023. .

Paper accepted at AAAI Doctoral Consortium 2023

Oct 11, 2022

The work Topics in Selective Classification has been accepted at the Doctoral Consortium of AAAI Conference on Artificial Intelligence (AAAI) 2023. A huge thanks to my PhD supervisor Salvatore Ruggieri for his help.