From inexact optimization to learning via gradient concentration

DOI10.1007/S10589-022-00408-5OpenAlexW3166001443MaRDI QIDQ2111477FDOQ2111477

Authors: Bernhard Stankewitz, Nicole Mücke, Lorenzo Rosasco 

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

Recommendations

• Deep learning: a statistical viewpoint
• scientific article; zbMATH DE number 1786133
• Non-asymptotic convergence analysis of inexact gradient methods for machine learning without strong convexity
• Regularization techniques and suboptimal solutions to optimization problems in learning from data
• Optimization problems for machine learning: a survey

zbMATH Keywords

kernel methodsstatistical learningimplicit regularization

Mathematics Subject Classification ID

Stochastic programming (90C15)

Cites Work

• Nonparametric stochastic approximation with large step-sizes
• Support Vector Machines
• High-Dimensional Statistics
• High-Dimensional Probability
• Concentration inequalities. A nonasymptotic theory of independence
• 10.1162/153244302760200704
• On early stopping in gradient descent learning
• Understanding Machine Learning
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• 10.1162/153244303321897690
• Title not available (Why is that?)
• Gradient Convergence in Gradient methods with Errors
• An Iteration Formula for Fredholm Integral Equations of the First Kind
• Divide and conquer kernel ridge regression: a distributed algorithm with minimax optimal rates
• Title not available (Why is that?)
• On regularization algorithms in learning theory
• Convex optimization: algorithms and complexity
• Optimal rates for regularization of statistical inverse learning problems
• Robust Estimation via Robust Gradient Estimation
• Convergence rates of kernel conjugate gradient for random design regression
• Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
• Early stopping for statistical inverse problems via truncated SVD estimation
• Optimal Rates for Multi-pass Stochastic Gradient Methods
• Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression
• Title not available (Why is that?)
• Iterative regularization for learning with convex loss functions
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Vector-Contraction Inequality for Rademacher Complexities
• Title not available (Why is that?)
• Graph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient Descent
• Early Stopping for Kernel Boosting Algorithms: A General Analysis With Localized Complexities

Cited In (12)

• Title not available (Why is that?)
• The importance of convexity in learning with squared loss
• Special issue for SIMAI 2020-2021: large-scale optimization and applications
• Title not available (Why is that?)
• Gradient-Based Discrete-Time Concurrent Learning for Standalone Function Approximation
• Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data
• Implicit regularization with strongly convex bias: Stability and acceleration
• Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
• Towards an automatic uncertainty compiler
• From inexact optimization to learning via gradient concentration
• A Note on Lewicki-Sejnowski Gradient for Learning Overcomplete Representations
• Approximation and learning of convex superpositions

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2111477)