Optimal large-scale stochastic optimization of NDCG surrogates for deep learning

DOI10.1007/S10994-024-06631-XMaRDI QIDQ6984770zbMATH OpenFDO

Authors Zi-Hao Qiu, Quanqi Hu, Yongjian Zhong, Weiwei Tu, Lijun Zhang, Tianbao Yang

Publication date 14 May 2025

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10994-024-06631-X

zbMATH Keywords

information retrievalNDCGnonconvex optimizationstochastic optimization

Mathematics Subject Classification ID

Information storage and retrieval of data (68P20) Artificial neural networks and deep learning (68T07) Stochastic programming (90C15) Nonconvex programming, global optimization (90C26) Applications of mathematical programming (90C90)

Cites work

• A bilevel optimization approach for parameter learning in variational models
• A Two-Timescale Stochastic Algorithm Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic
• An overview of bilevel optimization
• Learning to Rank for Information Retrieval
• Lower bounds for non-convex stochastic optimization
• RSG: Beating Subgradient Method without Smoothness and Strong Convexity
• Smooth minimization of non-smooth functions
• Solving Stochastic Compositional Optimization is Nearly as Easy as Solving Stochastic Optimization
• Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Stochastic multilevel composition optimization algorithms with level-independent convergence rates
• Stochastic nested variance reduction for nonconvex optimization

This page was built for publication: Optimal large-scale stochastic optimization of NDCG surrogates for deep learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6984770)