I am a second year Ph.D. student in Computer Science at the University of Waterloo, and a member of the OpAL lab.
My advisor is Kimon Fountoulakis, and my research focuses on learning algorithms using neural networks. I am also broadly interested at the intersection of theoretical machine learning and graphs.
Previously, I obtained a MSc in Artificial Intelligence and Robotics at Sapienza University of Rome, and a BSc in Mechanical Engineering at the Federal University of Santa Catarina.
In Summer 2025, I am joining Amazon NY as an Applied Scientist Intern in the SCOT Forecasting team. Prior to that, in 2022, I interned at Huawei's Noah's Ark Lab, focusing on Federated Learning and Domain Generalization with Guojun Zhang, and exploring invariant graph representations with Yingxue Zhang.
Publications
- Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks
Artur Back de Luca, George Giapitzakis & Kimon Fountoulakis.
Preprint, 2025
- Exact Learning of Permutations for Nonzero Binary Inputs with Logarithmic Training Size and Quadratic Ensemble Complexity
George Giapitzakis, Artur Back de Luca & Kimon Fountoulakis.
High-dimensional Learning Dynamics Workshop @ ICML (to appear), 2025
- Positional Attention: Expressivity and Learnability of Algorithmic Computation
Artur Back de Luca, George Giapitzakis, Shenghao Yang, Petar Veličković & Kimon Fountoulakis.
ICML (to appear), 2025
- Simulation of Graph Algorithms with Looped Transformers
Artur Back de Luca & Kimon Fountoulakis.
ICML, 2024
- Local Graph Clustering with Noisy Labels
Artur Back de Luca, Kimon Fountoulakis & Shenghao Yang.
ICLR, 2024
- Mitigating Data Heterogeneity in Federated Learning with Data Augmentation
Artur Back de Luca, Guojun Zhang, Xi Chen & Yaoliang Yu.
Preprint, 2022