no code implementations • 1 Apr 2024 • Zelin He, Ying Sun, Jingyuan Liu, Runze Li
Nonasymptotic bound is provided for the estimation error of the target model, showing the robustness of the proposed method to covariate shifts.
no code implementations • 20 Mar 2024 • Zelin He, Ying Sun, Jingyuan Liu, Runze Li
We consider the transfer learning problem in the high dimensional setting, where the feature dimension is larger than the sample size.
1 code implementation • 11 Feb 2022 • Runlong Zhou, Zelin He, Yuandong Tian, Yi Wu, Simon S. Du
Furthermore, our theory explains the benefit of curriculum learning: it can find a strong sampling policy and reduce the distribution shift, a critical quantity that governs the convergence rate in our theorem.