Quétu, V. and Tartaglione, E. 2024. DSD²: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?. Proceedings of the AAAI Conference on Artificial Intelligence. 38, 13 (Mar. 2024), 14749-14757. DOI:https://doi.org/10.1609/aaai.v38i13.29393.