Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits

21 January 2019

Papers citing "Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits"

6 / 6 papers shown

Title
Nonparametric Teaching for Graph Property Learners Chen Zhang Weixin Bu Zhaochun Ren Ziyue Liu Yik-Chung Wu Ngai Wong 54 0 0 20 May 2025
SGD with memory: fundamental properties and stochastic acceleration Dmitry Yarotsky Maksim Velikanov 50 1 0 05 Oct 2024
Surprises in High-Dimensional Ridgeless Least Squares Interpolation Trevor Hastie Andrea Montanari Saharon Rosset Robert Tibshirani 94 737 0 19 Mar 2019
Reconciling modern machine learning practice and the bias-variance trade-off M. Belkin Daniel J. Hsu Siyuan Ma Soumik Mandal 150 1,628 0 28 Dec 2018
Gradient Descent Quantizes ReLU Network Features Hartmut Maennel Olivier Bousquet Sylvain Gelly MLT 26 80 0 22 Mar 2018
The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning Siyuan Ma Raef Bassily M. Belkin 41 289 0 18 Dec 2017