| Rigorous dynamical mean-field theory for stochastic gradient descent methods C Gerbelot, E Troiani, F Mignacco, F Krzakala, L Zdeborova SIAM Journal on Mathematics of Data Science 6 (2), 400-427, 2024 | 67 | 2024 |
| The benefits of reusing batches for gradient descent in two-layer networks: Breaking the curse of information and leap exponents Y Dandi, E Troiani, L Arnaboldi, L Pesce, L Zdeborová, F Krzakala Forty-second International Conference on Machine Learning, 2024 | 58 | 2024 |
| Could ChatGPT get an engineering degree? Evaluating higher education vulnerability to AI assistants B Borges, N Foroutan, D Bayazit, A Sotnikova, S Montariol, T Nazaretsky, ... Proceedings of the National Academy of Sciences 121 (49), e2414955121, 2024 | 32 | 2024 |
| Fundamental computational limits of weak learnability in high-dimensional multi-index models E Troiani, Y Dandi, L Defilippis, L Zdeborová, B Loureiro, F Krzakala The 28th International Conference on Artificial Intelligence and Statistics, 2025 | 27* | 2025 |
| Optimal denoising of rotationally invariant rectangular matrices E Troiani, V Erba, F Krzakala, A Maillard, L Zdeborová Mathematical and Scientific Machine Learning 190, 97--112, 2022 | 21 | 2022 |
| Bayes-optimal learning of an extensive-width neural network from quadratically many samples A Maillard, E Troiani, S Martin, F Krzakala, L Zdeborová Advances in Neural Information Processing Systems 37, 82085-82132, 2024 | 20* | 2024 |
| Fundamental limits of learning in sequence multi-index models and deep attention networks: High-dimensional asymptotics and sharp thresholds E Troiani, H Cui, Y Dandi, F Krzakala, L Zdeborová Forty-second International Conference on Machine Learning, 2025 | 11 | 2025 |
| Bilinear sequence regression: A model for learning from long sequences of high-dimensional tokens V Erba, E Troiani, L Biggio, A Maillard, L Zdeborová Physical Review X 15 (2), 021092, 2025 | 8 | 2025 |
| Asymptotic characterisation of the performance of robust linear regression in the presence of outliers M Vilucchio, E Troiani, V Erba, F Krzakala International Conference on Artificial Intelligence and Statistics, 811-819, 2024 | 7* | 2024 |
| The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks V Erba, E Troiani, L Zdeborová, F Krzakala arXiv preprint arXiv:2505.17958, 2025 | 5 | 2025 |
| Gibbs sampling the posterior of neural networks G Piccioli, E Troiani, L Zdeborova Journal of Physics A: Mathematical and Theoretical 57 (12), 125002, 2024 | 4 | 2024 |
| Scaling laws and spectra of shallow neural networks in the feature learning regime L Defilippis, Y Xu, J Girardin, E Troiani, V Erba, L Zdeborová, B Loureiro, ... arXiv preprint arXiv:2509.24882, 2025 | 3 | 2025 |
| Sparse representations, inference and learning C Lauditi, E Troiani, M Mézard Journal of Statistical Mechanics: Theory and Experiment 2024 (10), 104001, 2024 | 3 | 2024 |
| Bayes optimal learning of attention-indexed models F Boncoraglio, E Troiani, V Erba, L Zdeborová arXiv preprint arXiv:2506.01582, 2025 | 2 | 2025 |
| Stuttering Conway Sequences Are Still Conway Sequences É Brier, R Géraud-Stewart, D Naccache, A Pacco, E Troiani arXiv preprint arXiv:2006.06837, 2020 | 2 | 2020 |
| Inductive bias and spectral properties of single-head attention in high dimensions F Boncoraglio, V Erba, E Troiani, F Krzakala, L Zdeborová arXiv preprint arXiv:2509.24914, 2025 | 1 | 2025 |
| The Look-and-Say The Biggest Sequence Eventually Cycles É Brier, R Géraud-Stewart, D Naccache, A Pacco, E Troiani arXiv preprint arXiv:2006.07246, 2020 | | 2020 |
Lenka ZdeborováEPFL, SwitzerlandVerified email at epfl.ch
