Dimension independent excess risk by stochastic gradient descent

DOI10.1214/22-EJS2055MaRDI QIDQ2084455

Xi Chen, Qiang Liu, Xin Thomson Tong

Publication date: 18 October 2022

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2003.11196

zbMATH Keywords

regularizationstochastic gradient descentexcess riskdimension independentweak non-convexity

Mathematics Subject Classification ID

Statistics (62-XX) Biology and other natural sciences (92-XX) Numerical analysis (65-XX) Computer science (68-XX)

Uses Software

• fda (R)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nonparametric stochastic approximation with large step-sizes
• Prediction in functional linear regression
• Functional additive regression
• Methodology and convergence rates for functional linear regression
• Surprises in high-dimensional ridgeless least squares interpolation
• Bridging the gap between constant step size stochastic gradient descent and Markov chains
• Sequential complexities and uniform martingale laws of large numbers
• First-order and stochastic optimization methods for machine learning
• Functional data analysis.
• Optimal Rates for Multi-pass Stochastic Gradient Methods
• Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression
• Optimization Methods for Large-Scale Machine Learning
• Two Models of Double Descent for Weak Features
• Benign overfitting in linear regression
• Reconciling modern machine-learning practice and the classical bias–variance trade-off
• Optimal Estimation of Genetic Relatedness in High-Dimensional Linear Models
• Understanding Machine Learning
• Learning Bounds for Kernel Regression Using Effective Data Dimensionality
• A Stochastic Approximation Method

This page was built for publication: Dimension independent excess risk by stochastic gradient descent