Max-affine regression via first-order methods

DOI10.1137/23M1594662MaRDI QIDQ6583522zbMATH OpenFDO

Authors Seonho Kim, Kiryung Lee

Publication date 6 August 2024

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/23M1594662

zbMATH Keywords

gradient descentmax-affine regressionnonconvex optimizationstochastic gradient descent

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26)

Recommendations

• Composite difference-MAX programs for modern statistical estimation problems
• A sparsity preserving stochastic gradient methods for sparse regression
• Spectrahedral Regression
• On the regularizing property of stochastic gradient descent
• On stochastic accelerated gradient with convergence rate of regression learning

Cites work

• 10.1162/15324430260185628
• A nonconvex approach for phase retrieval: reshaped Wirtinger flow and incremental algorithms
• Advances and Open Problems in Federated Learning
• Consistency of multidimensional convex regression
• Convex piecewise-linear fitting
• Covering Numbers for Convex Functions
• Deep learning
• Dynamics of stochastic gradient descent for two-layer neural networks in the teacher–student setup*
• Fitting piecewise linear continuous functions
• Generalized Gradients and Applications
• High-dimensional probability. An introduction with applications in data science
• scientific article; zbMATH DE number 3737398 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• Max-Affine Regression: Parameter Estimation for Gaussian Designs
• Multivariate convex regression with adaptive partitioning
• Optimization methods for large-scale machine learning
• Phase retrieval via randomized Kaczmarz: theoretical guarantees
• Phase Retrieval via Reweighted Amplitude Flow
• Reinforcement learning. An introduction
• Robust Stochastic Approximation Approach to Stochastic Programming
• Statistical mechanics of learning
• Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm

Cited in

(1)

• Input convex Kolmogorov-Arnold networks

This page was built for publication: Max-affine regression via first-order methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6583522)