Emanuele Troiani
Scholar

Emanuele Troiani

Google Scholar ID: Gh0snLcAAAAJ
École polytechnique fédérale de Lausanne
Google Scholar↗
Citations & Impact
All-time
Citations
227
 
H-index
7
 
i10-index
6
 
Publications
17
 
Co-authors
10
list available
Contact
No contact links provided.
Publications
8 items
A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization
2026
Cited
0
Inductive Bias and Spectral Properties of Single-Head Attention in High Dimensions
2025
Cited
0
Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
2025
Cited
0
Bayes optimal learning of attention-indexed models
2025
Cited
0
The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
2025
Cited
0
Fundamental limits of learning in sequence multi-index models and deep attention networks: High-dimensional asymptotics and sharp thresholds
2025
Cited
0
Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens
arXiv.org · 2024
Cited
0
Fundamental computational limits of weak learnability in high-dimensional multi-index models
2024
Cited
2
Resume (English only)
Co-authors
10 total
Lenka Zdeborová
Lenka Zdeborová
EPFL, Switzerland
Florent Krzakala
Florent Krzakala
École polytechnique fédérale de Lausanne
Yatin Dandi
Yatin Dandi
EPFL, IIT Kanpur
Vittorio Erba
Vittorio Erba
EPFL, Lausanne
Antoine Maillard
Antoine Maillard
Inria Paris
Cedric Gerbelot
Cedric Gerbelot
Ecole Normale Supérieure de Lyon
Francesca Mignacco
Francesca Mignacco
Princeton University & City University of New York
Luca Arnaboldi
Luca Arnaboldi
PhD Student, EPFL