From inexact optimization to learning via gradient concentration

DOI10.1007/s10589-022-00408-5OpenAlexW3166001443MaRDI QIDQ2111477

Nicole Mücke, Lorenzo Rosasco, Bernhard Stankewitz

Publication date: 16 January 2023

Published in: Computational Optimization and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2106.05397

zbMATH Keywords

kernel methodsstatistical learningimplicit regularization

Mathematics Subject Classification ID

Stochastic programming (90C15)

Related Items (2)

Towards an automatic uncertainty compiler ⋮ Special issue for SIMAI 2020-2021: large-scale optimization and applications

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
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• Optimal rates for regularization of statistical inverse learning problems
• On regularization algorithms in learning theory
• Early stopping for statistical inverse problems via truncated SVD estimation
• Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
• On early stopping in gradient descent learning
• Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates
• Iterative Regularization for Learning with Convex Loss Functions
• A Vector-Contraction Inequality for Rademacher Complexities
• Convergence rates of Kernel Conjugate Gradient for random design regression
• Support Vector Machines
• Gradient Convergence in Gradient methods with Errors
• High-Dimensional Statistics
• Optimal Rates for Multi-pass Stochastic Gradient Methods
• Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression
• High-Dimensional Probability
• 10.1162/153244302760200704
• 10.1162/153244303321897690
• Graph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient Descent
• Robust Estimation via Robust Gradient Estimation
• Early Stopping for Kernel Boosting Algorithms: A General Analysis With Localized Complexities
• Understanding Machine Learning
• An Iteration Formula for Fredholm Integral Equations of the First Kind

This page was built for publication: From inexact optimization to learning via gradient concentration