Every month, the joint laboratory invites external speakers to take part in seminars for its partners.
Enzo Tartaglione (Télécom Paris): “Efficiency by Pruning in Deep Learning”
Abstract: As Deep Learning is one of the most privileged methods for solving a specific task, growing concerns about computation required both at training and inference are posed. Multiple approaches can be taken to try countering computational complexity: in this talk, we will cover pruning as a possible method to enhance efficiency. We will uncover a historical roadmap for it, and present some of the most recent advances for both efficient training and inference of Deep Models, applied to most recent architectures and Hardware, at both large and small scales.
Bio: Enzo Tartaglione is Maitre de Conferences at Telecom Paris and he is an Hi!Paris chair holder. He is also Member of the ELLIS Society and Associate Editor of IEEE Transactions on Neural Networks and Learning Systems. He has received the MS degree in Electronic Engineering at Politecnico di Torino in 2015, cum laude. The same year, he also received a magna cum laude MS in electrical and computer engineering at University of Illinois at Chicago. In 2016 he was also awarded the MS in Electronics by Politecnico di Milano, cum laude. In 2019 he obtained the PhD in Physics at Politecnico di Torino, cum laude, with the thesis “From Statistical Physics to Algorithms in Deep Neural Systems”. His principal interests include compression, sparsification, pruning and watermarking of deep neural networks, deep learning for medical imaging, privacy-aware learning, data debiasing, regularization for deep learning and neural networks growing. His expertise mainly focuses on the themes of efficient deep learning, with articles published on top conferences and journals in the field.
