Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods

30 May 2022

Papers citing "Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods"

4 / 4 papers shown

Title
Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks Fanghui Liu L. Dadi V. Cevher 74 2 0 29 Apr 2024
Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping Umut Simsekli Mert Gurbuzbalaban S. Yıldırım Lingjiong Zhu 38 2 0 04 Mar 2024
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent Lingjiong Zhu Mert Gurbuzbalaban Anant Raj Umut Simsekli 24 6 0 20 May 2023
A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network Mo Zhou Rong Ge Chi Jin 69 44 0 04 Feb 2021