Asymptotic theory of in-context learning by linear attention YM Lu, MI Letey, JA Zavatone-Veth, A Maiti, C Pehlevan arXiv preprint arXiv:2405.11751, 2024 | 3 | 2024 |
Asymptotics of random feature regression beyond the linear scaling regime H Hu, YM Lu, T Misiakiewicz arXiv preprint arXiv:2403.08160, 2024 | 3 | 2024 |
A convergence analysis of approximate message passing with non-separable functions and applications to multi-class classification B Çakmak, YM Lu, M Opper arXiv preprint arXiv:2402.08676, 2024 | 2 | 2024 |
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 | 7 | 2024 |
Precise Learning Curves and Higher-Order Scaling Limits for Dot Product Kernel Regression L Xiao, H Hu, T Misiakiewicz, YM Lu, J Pennington Journal of Statistical Mechanics: Theory and Experiment 2023 (11), 114005, 2023 | 1 | 2023 |
Universality for the global spectrum of random inner-product kernel matrices in the polynomial regime S Dubova, YM Lu, B McKenna, HT Yau arXiv preprint arXiv:2310.18280, 2023 | 3 | 2023 |
Universality of approximate message passing with semirandom matrices R Dudeja, Y M. Lu, S Sen The Annals of Probability 51 (5), 1616-1683, 2023 | 40 | 2023 |
An equivalence principle for the spectrum of random inner-product kernel matrices YM Lu, HT Yau Annals of Applied Probability, under minor revision, 2023 | 24 | 2023 |
Universality laws for high-dimensional learning with random features H Hu, YM Lu IEEE Transactions on Information Theory 69 (3), 1932-1964, 2022 | 143 | 2022 |
Spectral universality of regularized linear regression with nearly deterministic sensing matrices R Dudeja, S Sen, YM Lu arXiv preprint arXiv:2208.02753, 2022 | 21 | 2022 |
SLOPE for sparse linear regression: asymptotics and optimal regularization H Hu, YM Lu IEEE Transactions on Information Theory 68 (11), 7627-7664, 2022 | 2 | 2022 |
Analysis of random sequential message passing algorithms for approximate inference B Çakmak, YM Lu, M Opper Journal of Statistical Mechanics: Theory and Experiment 2022 (7), 073401, 2022 | 2 | 2022 |
Sharp asymptotics of kernel ridge regression beyond the linear regime H Hu, YM Lu arXiv preprint arXiv:2205.06798, 2022 | 18 | 2022 |
An Equivalence Principle for the Spectrum of Random Inner-Product Kernel Matrices with Polynomial Scalings YM Lu, HT Yau arXiv preprint arXiv:2205.06308, 2022 | 3 | 2022 |
Construction of optimal spectral methods in phase retrieval A Maillard, F Krzakala, YM Lu, L Zdeborová Mathematical and Scientific Machine Learning, 693-720, 2022 | 13 | 2022 |
Householder dice: A matrix-free algorithm for simulating dynamics on Gaussian and random orthogonal ensembles YM Lu IEEE Transactions on Information Theory 67 (12), 8264-8272, 2021 | 11 | 2021 |
On the inherent regularization effects of noise injection during training O Dhifallah, Y Lu International Conference on Machine Learning, 2665-2675, 2021 | 29 | 2021 |
Phase transitions in transfer learning for high-dimensional perceptrons O Dhifallah, YM Lu Entropy 23 (4), 400, 2021 | 19 | 2021 |
The limiting poisson law of massive MIMO detection with box relaxation H Hu, YM Lu IEEE Journal on Selected Areas in Information Theory 1 (3), 695-704, 2020 | 2 | 2020 |
The role of regularization in classification of high-dimensional noisy gaussian mixture F Mignacco, F Krzakala, Y Lu, P Urbani, L Zdeborova International conference on machine learning, 6874-6883, 2020 | 87 | 2020 |