On the discrepancy principle for stochastic gradient descent

DOI10.1088/1361-6420/abaa58OpenAlexW3046122974MaRDI QIDQ5123704

Bangti Jin, Tim Jahn

Publication date: 29 September 2020

Published in: Inverse Problems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2004.14625

zbMATH Keywords

convergencediscrepancy principlestochastic gradient descent

Mathematics Subject Classification ID

Nonparametric inference (62Gxx) General theory of linear operators (47Axx) Miscellaneous applications of operator theory (47Nxx)

Related Items (5)

Stochastic asymptotical regularization for linear inverse problems ⋮ Stochastic mirror descent method for linear ill-posed problems in Banach spaces ⋮ Stochastic linear regularization methods: random discrepancy principle and applications ⋮ On the Convergence of Stochastic Gradient Descent for Linear Inverse Problems in Banach Spaces ⋮ An analysis of stochastic variance reduced gradient for linear inverse problems ^*

Uses Software

• Regularization tools

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Beyond the Bakushinkii veto: regularising linear inverse problems without knowing the noise distribution
• Iterative regularization methods for nonlinear ill-posed problems
• Regularization tools version \(4.0\) for matlab \(7.3\)
• Inverse Problems
• Discrepancy principle for statistical inverse problems with application to conjugate gradient iteration
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Optimization Methods for Large-Scale Machine Learning
• On the regularizing property of stochastic gradient descent
• On the Convergence of Stochastic Gradient Descent for Nonlinear Ill-Posed Problems
• An Iteration Formula for Fredholm Integral Equations of the First Kind
• A Stochastic Approximation Method

This page was built for publication: On the discrepancy principle for stochastic gradient descent