| How two-layer neural networks learn, one (giant) step at a time Y Dandi, F Krzakala, B Loureiro, L Pesce, L Stephan arXiv preprint arXiv:2305.18270, 2023 | 107 | 2023 |
| 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 arXiv preprint arXiv:2402.03220, 2024 | 58 | 2024 |
| Sampling with flows, diffusion, and autoregressive neural networks from a spin-glass perspective D Ghio, Y Dandi, F Krzakala, L Zdeborová Proceedings of the National Academy of Sciences 121 (27), e2311810121, 2024 | 56 | 2024 |
| Implicit gradient alignment in distributed and federated learning Y Dandi, L Barba, M Jaggi Proceedings of the AAAI Conference on Artificial Intelligence 36 (6), 6454-6462, 2022 | 48 | 2022 |
| Repetita iuvant: Data repetition allows sgd to learn high-dimensional multi-index functions L Arnaboldi, Y Dandi, F Krzakala, L Pesce, L Stephan arXiv preprint arXiv:2405.15459, 2024 | 35 | 2024 |
| Universality laws for gaussian mixtures in generalized linear models Y Dandi, L Stephan, F Krzakala, B Loureiro, L Zdeborová Advances in Neural Information Processing Systems 36, 54754-54768, 2023 | 35 | 2023 |
| Asymptotics of feature learning in two-layer networks after one gradient-step H Cui, L Pesce, Y Dandi, F Krzakala, YM Lu, L Zdeborová, B Loureiro arXiv preprint arXiv:2402.04980, 2024 | 34 | 2024 |
| Data-heterogeneity-aware mixing for decentralized learning Y Dandi, A Koloskova, M Jaggi, SU Stich arXiv preprint arXiv:2204.06477, 2022 | 31 | 2022 |
| Universality laws for gaussian mixtures in generalized linear models Y Dandi, L Stephan, F Krzakala, B Loureiro, L Zdeborová Journal of Statistical Mechanics: Theory and Experiment 2024 (10), 104015, 2024 | 19 | 2024 |
| Fundamental limits of weak learnability in high-dimensional multi-index models E Troiani, Y Dandi, L Defilippis, L Zdeborová, B Loureiro, F Krzakala High-dimensional Learning Dynamics 2024: The Emergence of Structure and …, 2024 | 17 | 2024 |
| A random matrix theory perspective on the spectrum of learned features and asymptotic generalization capabilities Y Dandi, L Pesce, H Cui, F Krzakala, YM Lu, B Loureiro arXiv preprint arXiv:2410.18938, 2024 | 15 | 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 arXiv preprint arXiv:2502.00901, 2025 | 11 | 2025 |
| Maximally-stable local optima in random graphs and spin glasses: phase transitions and universality Y Dandi, D Gamarnik, L Zdeborová arXiv preprint arXiv:2305.03591, 2023 | 11 | 2023 |
| Online learning and information exponents: On the importance of batch size, and time/complexity tradeoffs L Arnaboldi, Y Dandi, F Krzakala, B Loureiro, L Pesce, L Stephan arXiv preprint arXiv:2406.02157, 2024 | 10 | 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 arXiv preprint arXiv:2405.15480, 2024 | 10 | 2024 |
| Jointly trained image and video generation using residual vectors Y Dandi, A Das, S Singhal, V Namboodiri, P Rai Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2020 | 10 | 2020 |
| Generalized Adversarially Learned Inference Y Dandi, H Bharadhwaj, A Kumar, P Rai AAAI, 2021, 2020 | 8 | 2020 |
| Optimal spectral transitions in high-dimensional multi-index models L Defilippis, Y Dandi, P Mergny, F Krzakala, B Loureiro arXiv preprint arXiv:2502.02545, 2025 | 7 | 2025 |
| Implicit gradient alignment in distributed and federated learning L Barba, M Jaggi, Y Dandi AAAI Conference on Artificial Intelligence, AAAI 22, 2021 | 7 | 2021 |
| Asymptotics of non-convex generalized linear models in high-dimensions: A proof of the replica formula M Vilucchio, Y Dandi, MP Rossignol, C Gerbelot, F Krzakala arXiv preprint arXiv:2502.20003, 2025 | 6 | 2025 |
Florent KrzakalaÉcole polytechnique fédérale de LausanneVerified email at epfl.ch
