Li, Mufan

8 publications

NeurIPS 2025 Don't Be Lazy: CompleteP Enables Compute-Efficient Deep Transformers Nolan Simran Dey, Bin Claire Zhang, Lorenzo Noci, Mufan Li, Blake Bordelon, Shane Bergsma, Cengiz Pehlevan, Boris Hanin, Joel Hestness

COLT 2024 Sampling from the Mean-Field Stationary Distribution Yunbum Kook, Matthew S. Zhang, Sinho Chewi, Murat A. Erdogdu, Mufan Li

NeurIPSW 2023 Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit Blake Bordelon, Lorenzo Noci, Mufan Li, Boris Hanin, Cengiz Pehlevan

COLT 2023 Improved Discretization Analysis for Underdamped Langevin Monte Carlo Shunshi Zhang, Sinho Chewi, Mufan Li, Krishna Balasubramanian, Murat A. Erdogdu

NeurIPS 2023 The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit Lorenzo Noci, Chuning Li, Mufan Li, Bobby He, Thomas Hofmann, Chris J Maddison, Dan Roy

COLT 2022 Analysis of Langevin Monte Carlo from Poincare to Log-Sobolev Sinho Chewi, Murat A Erdogdu, Mufan Li, Ruoqi Shen, Shunshi Zhang

NeurIPS 2022 The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization Mufan Li, Mihai Nica, Dan Roy

NeurIPS 2021 The Future Is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization Mufan Li, Mihai Nica, Dan Roy