Seguir
Mufan (Bill) Li
Mufan (Bill) Li
Princeton University
Dirección de correo verificada de princeton.edu - Página principal
Título
Citado por
Citado por
Año
Analysis of Langevin Monte Carlo from Poincar\'e to Log-Sobolev
S Chewi, MA Erdogdu, MB Li, R Shen, M Zhang
Foundations of Computational Mathematics, 1-51, 2024
1132024
The future is log-Gaussian: ResNets and their infinite-depth-and-width limit at initialization
M Li, M Nica, D Roy
Advances in Neural Information Processing Systems 34, 7852-7864, 2021
412021
Riemannian Langevin Algorithm for Solving Semidefinite Programs
MB Li, MA Erdogdu
Bernoulli 29 (4), 3093-3113, 2023
372023
The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization
M Li, M Nica, D Roy
Advances in Neural Information Processing Systems 35, 10795-10808, 2022
372022
Improved discretization analysis for underdamped Langevin Monte Carlo
S Zhang, S Chewi, M Li, K Balasubramanian, MA Erdogdu
The Thirty Sixth Annual Conference on Learning Theory, 36-71, 2023
322023
The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit
L Noci, C Li, M Li, B He, T Hofmann, CJ Maddison, D Roy
Advances in Neural Information Processing Systems 36, 2023
312023
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
B Bordelon, L Noci, MB Li, B Hanin, C Pehlevan
International Conference on Learning Representations, 2024
162024
Sampling from the mean-field stationary distribution
Y Kook, MS Zhang, S Chewi, MA Erdogdu, MB Li
The Thirty Seventh Annual Conference on Learning Theory, 3099-3136, 2024
82024
Differential Equation Scaling Limits of Shaped and Unshaped Neural Networks
MB Li, M Nica
Transactions on Machine Learning Research, 2024
22024
Higher Order Generalization Error for First Order Discretization of Langevin Diffusion
MB Li, M Gazeau
arXiv preprint arXiv:2102.06229, 2021
12021
Analysis of Learning Algorithms via Diffusion Limits
M Li
2023
Acceleration of gossip algorithms through the Euler–Poisson–Darboux Equation
R Berthier, M Li
IMA Journal of Applied Mathematics 87 (6), 985-1009, 2022
2022
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–12