Luca Arnaboldi

Orcid: 0009-0001-9739-8849

Affiliations:
  • École Polytechnique Fédérale de Lausanne (EPFL), IdePHICS Lab, Lausanne, Switzerland


According to our database1, Luca Arnaboldi authored at least 3 papers between 2023 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents.
CoRR, 2024

2023
Escaping mediocrity: how two-layer networks learn hard single-index models with SGD.
CoRR, 2023

From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks.
Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023


  Loading...