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 9 papers between 2023 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning.

[BibT_eX]

[DOI]

CoRR, May, 2026

ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models.

[BibT_eX]

[DOI]

CoRR, February, 2026

2025

Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks.

[BibT_eX]

[DOI]

CoRR, June, 2025

2024

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs.

[BibT_eX]

[DOI]

CoRR, 2024

Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions.

[BibT_eX]

[DOI]

CoRR, 2024

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

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

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

[BibT_eX]

[DOI]

CoRR, 2023

From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Luca Arnaboldi

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...