Enzo Tartaglione

Fellows

Full Professor

• Télécom Paris (IP Paris)

Research topics

Green AI

•

Privacy in AI

•

Model Debiasing

•

Model Compression

Biography

Enzo Tartaglione is a Full Professor at Télécom Paris (Institut Polytechnique de Paris), where he is also responsible for the group Multimedia, Hi! PARIS Fellow, member of the ELLIS society, Senior member of IEEE, Associate Editor of IEEE Transactions on Neural Networks and Learning Systems since 2024, of Transactions on Machine Learning Research since 2025, and of the EURASIP Journal on Image and Video Processing since 2025. He received the MS in Electronic Engineering at Politecnico di Torino and Politecnico di Milano in 2015, cum laude. The same year, he also received a magna cum laude MS in electrical and computer engineering at the University of Illinois at Chicago. In 2019 he obtained a Ph.D. in Physics at Politecnico di Torino, cum laude, with the thesis “From Statistical Physics to Algorithms in Deep Neural Systems” and in 2024 his HDR. He is an Area Chair in top AI venues and has been nominated outstanding reviewer three times in these. Besides, he was keynote speaker at PCS 2025 and a finalist for the 2025 Multimedia Rising Star Award. His principal interests include compression, sparsification, pruning of deep neural networks, computer vision, debiasing, 3D Gaussian Splatting, and regularization for deep learning.

His Hi! PARIS fellowship project focuses on combining artificial intelligence, econometric modeling, and alternative data to better understand and anticipate economic and financial dynamics.

The project aims to improve the real-time monitoring of macroeconomic activity by developing AI models capable of detecting business cycle regimes and producing timely, interpretable forecasts. By leveraging high-frequency and heterogeneous data sources, including alternative and climate-related data, it seeks to capture early signals often missed by traditional indicators. The research also explores how climate shocks and policy responses impact key economic variables such as inflation. By integrating advanced forecasting methods with interpretability tools, the project contributes to more informed and responsive economic decision-making.