Events

Title: "Causethical ML: from theory to practice"

Abstract: In this talk I will give an overview of the role of causality in ethical machine learning, and in particular, in fair and explainable ML. In particular, I will first detail how to use causal reasoning to study fairness and interpretability problems in algorithmic decision making, stressing the main limitations that we encounter when aiming to address these problems in practice.  Then, I will provide some hints about how to solve some of these practical limitations by using causal generative models. A novel class of deep generative models that do not only accurately fit observational data but can also provide accurate estimates to interventional and counterfactual queries. I will finally discussed the open challenges of designing such causal generative models.

Bio: Isabel Valera is Full Professor of Machine Learning at the Department of Computer Science at Saarland University (Saarbrücken, Germany), and Adjunct Faculty at the MPI for Software Systems in Saarbrücken (Saarbrücken, Germany). She is the recipient of an ERC Starting Grant on "Society-Aware ML", and a Fellow of the European Laboratory for Learning and Intelligent Systems (ELLIS). Previously, she was an independent group leader at the MPI for Intelligent Systems in Tübingen, Germany.  She received her Ph.D. in 2014 and her MSc in 2012 from the University Carlos III in Madrid, Spain, and worked as a postdoctoral researcher at the MPI for Software Systems (Germany) and the University of Cambridge (UK).  Her research focuses on the development of trustworthy machine learning methods that can be used in the real world.  Her research can be broadly categorized into three main themes: fair, interpretable, and robust machine learning. Her research interests cover a wide range of ML approaches, including deep learning, probabilistic modeling, causal inference, time series analysis, and many more.

Para entrar en la reunión, pulse el siguiente enlace:
https://oficinavirtual.ugr.es/redes/SOR/SALVEUGR/accesosala.jsp?IDSALA=22996366
- Contraseña de la reunión: 966861

Title: Sustainable, Accurate, Fair and Trustworthy Artificial Intelligence

Abstract: The growth of Artificial Intelligence applications requires to develop risk management models that can balance opportunities with risks. In the talk, we contribute to the development of Artificial Intelligence risk models presenting a set of integrated statistical metrics that can measure the ``Sustainability'', ``Accuracy'', ``Fairness'' and ``Explainability'' of any Artificial Intelligence application, in line with  the requests of the European Artificial intelligence act. The proposed metrics are consistent with each other, as they are all derived from a common underlying statistical methodology.  They are very general and can be applied to any machine learning method, regardless of the underlying data and model. Their empirical validity will  be assessed by means of their practical application to a set of use cases. The application will reveal that the proposed metrics are more interpretable and more consistent with the expectations, with respect to standard metrics such as AUC, RMSE, Shapley values and classic fairness metrics.

Bio: Professor of Statistics at the University of Pavia and Professor of Machine learning at the European University Institute. Author of several scientific publications, with an h-index of 49  (Google scholar), 38 (Scopus),  33 (Web of Science). The publications propose statistical learning models that can measure risks and opportunities of high impact innovations, such as artificial intelligence and financial technologies. Chief Editor of the scientific journal "Statistics” (Taylor and Francis). Editor of  “Artificial Intelligence in Finance” (Frontiers) and  of "International journal of data science and analytics" (Springer). Coordinator of 13 funded scientific projects, among which the European Horizon2020 projects “PERISCOPE: Pan-European response to the impacts of covid-19 and future pandemics and epidemics (2020-2023)” and “FIN-TECH: Financial supervision and Technological compliance" (2019-2020). The projects have supported the research activity of 18 Phd students and of 13 Post-doc researchers. Research fellow at the Bank for International Settlements. Research expert for the European Commission, the European Insurance and Occupational Pensions Authority,  the Italian Ministry of Development, the Bank of Italy, the Italian Banking Association. Board member of the Credito Valtellinese bank (2010-2018). Honorary member of the  Italian Financial Risk Management Association. Elected fellow of the International Statistical Institute (ISI).  Member of the Institute of Mathematical Statistics (IMS), the Association for Computing Machinery (ACM), the  European Network for Business and Industrial Statistics (ENBIS), the Italian Statistical Society (SIS). See also: https://en.wiki.topitalianscientists.org/Paolo_Giudici

Para entrar en la reunión, pulse el siguiente enlace:
https://oficinavirtual.ugr.es/redes/SOR/SALVEUGR/accesosala.jsp?IDSALA=22996365
- Contraseña de la reunión: 785310