Access content directly

Arthur da Cunha

8
Documents

Publications

Image document

Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets

Arthur Carvalho Walraven da Cunha , Francesco d'Amore , Emanuele Natale
37th Conference on Neural Information Processing Systems (NeurIPS 2023), Dec 2023, New Orleans, United States. pp.25929-25957, ⟨10.5555/3666122.3667250⟩
Conference papers hal-04143024v2
Image document

Une implémentation GPU de la méthode de recherche approximative FlyHash

Arthur da Cunha , Damien Rivet , Emanuele Natale , Aurora Rossi
CAID 2023 - 5e Conference on Artificial Intelligence for Defense, DGA Maîtrise de l'Information, Nov 2023, Rennes, France
Conference papers hal-04328529v1
Image document

Neural Network Information Leakage through Hidden Learning

Arthur Carvalho Walraven da Cunha , Emanuele Natale , Laurent Viennot
OLA2023 - International Conference on Optimization and Learning, May 2023, Malaga, Spain. pp.117-128, ⟨10.1007/978-3-031-34020-8_8⟩
Conference papers hal-03157141v4
Image document

Revisiting the Random Subset Sum problem

Arthur Carvalho Walraven da Cunha , Francesco d'Amore , Frédéric Giroire , Hicham Lesfari , Emanuele Natale
31st Annual European Symposium on Algorithms (ESA 2023), Sep 2023, Amsterdam, Netherlands. pp.37:1--37:11, ⟨10.4230/LIPIcs.ESA.2023.37⟩
Conference papers hal-03654720v2
Image document

Proving the Strong Lottery Ticket Hypothesis for Convolutional Neural Networks

Arthur da Cunha , Emanuele Natale , Laurent Viennot
ICLR 2022 - 10th International Conference on Learning Representations, Apr 2022, Virtual, France
Conference papers hal-03548226v1
Image document

Pruning random structures

Arthur Carvalho Walraven da Cunha
Hardware Architecture [cs.AR]. Université Côte d'Azur, 2023. English. ⟨NNT : 2023COAZ4063⟩
Theses tel-04439889v2