Optimistic optimisation of composite objective with exponentiated update

DOI10.1007/s10994-022-06229-1arXiv2208.04065OpenAlexW4292663683MaRDI QIDQ6097136

Weijia Shao, Şahin Albayrak, Fikret Sivrikaya

Publication date: 12 June 2023

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2208.04065

zbMATH Keywords

sparsitycomposite objectiveexponetiated gradientonline convex optimisation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• A generalized online mirror descent with applications to classification and regression
• Exponentiated gradient versus gradient descent for linear predictors
• The robustness of the \(p\)-norm algorithms
• Introductory lectures on convex optimization. A basic course.
• Scale-free online learning
• First-order and stochastic optimization methods for machine learning
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Convexity and Optimization in Banach Spaces
• On the Generalization Ability of On-Line Learning Algorithms
• Improved Risk Tail Bounds for On-Line Algorithms
• Smoothed Low Rank and Sparse Matrix Recovery by Iteratively Reweighted Least Squares Minimization
• Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent

This page was built for publication: Optimistic optimisation of composite objective with exponentiated update