追蹤
Salma Tarmoun
Salma Tarmoun
在 sas.upenn.edu 的電子郵件地址已通過驗證
標題
引用次數
引用次數
年份
Understanding the Dynamics of Gradient Flow in Overparameterized Linear models
S Tarmoun, G Franca, BD Haeffele, R Vidal
International Conference on Machine Learning, 10153-10161, 2021
582021
On the explicit role of initialization on the convergence and implicit bias of overparametrized linear networks
H Min, S Tarmoun, R Vidal, E Mallada
International Conference on Machine Learning, 7760-7768, 2021
522021
Linear Convergence of Gradient Descent for Finite Width Over-parametrized Linear Networks with General Initialization
Z Xu, H Min, S Tarmoun, E Mallada, R Vidal
International Conference on Artificial Intelligence and Statistics, 2262-2284, 2023
62023
A LOCAL POLYAK-ŁOJASIEWICZ AND DESCENT LEMMA OF GRADIENT DESCENT FOR OVERPARAMETERIZED LINEAR MODELS
Z Xu, H Min, S Tarmoun, E Mallada, R Vidal
2023
Gradient Preconditioning for Non-Lipschitz smooth Nonconvex Optimization
S Tarmoun, S Slocum, BD Haeffele, R Vidal
2022
Implicit Acceleration of Gradient Flow in Overparameterized Linear Models
S Tarmoun, G França, BD Haeffele, R Vidal
2020
On the Explicit Role of Initialization on the Convergence and Generalization Properties of Overparametrized Linear Networks
H Min, S Tarmoun, R Vidal, E Mallada
2020
Learning Dynamics and Implicit Bias of Gradient Flow in Overparameterized Linear Models
R Vidal, S Tarmoun, H Min, B Haeffele, E Mallada, G Franca
2023 Joint Mathematics Meetings (JMM 2023), 0
系統目前無法執行作業,請稍後再試。
文章 1–8