Optimal survey schemes for stochastic gradient descent with applications to M-estimation

DOI10.1051/ps/2018021zbMath1420.62036arXiv1501.02218OpenAlexW2962901639MaRDI QIDQ4967801

Patrice Bertail, Stéphan Clémençon, Guillaume Papa, Emilie Chautru

Publication date: 11 July 2019

Published in: ESAIM: Probability and Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1501.02218

zbMATH Keywords

asymptotic analysiscentral limit theorem\(M\)-estimationstochastic gradient descentHorvitz-Thompson estimatorPoisson samplingsurvey scheme

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Sampling theory, sample surveys (62D05)

Related Items

Inversion-free subsampling Newton's method for large sample logistic regression ⋮ An Efficient Stochastic Newton Algorithm for Parameter Estimation in Logistic Regressions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Large sample theory of empirical distributions in biased sampling models
• Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing
• Rate of convergence to normal distribution for the Horvitz-Thompson estimator.
• Introductory lectures on convex optimization. A basic course.
• Weighted likelihood estimation under two-phase sampling
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Empirical Processes in Survey Sampling with (Conditional) Poisson Designs
• Theory of Classification: a Survey of Some Recent Advances
• A Z‐theorem with Estimated Nuisance Parameters and Correction Note for ‘Weighted Likelihood for Semiparametric Models and Two‐phase Stratified Samples, with Application to Cox Regression’
• Robust Stochastic Approximation Approach to Stochastic Programming
• On the Convergence of the Horvitz-Thompson Estimator
• Calibration Estimators in Survey Sampling
• Asymptotic Statistics
• Distributed Sparse Linear Regression
• Asymptotic Theory of Rejective Sampling with Varying Probabilities from a Finite Population
• Asymptotic Theory for Successive Sampling with Varying Probabilities Without Replacement, I
• A Generalization of Sampling Without Replacement From a Finite Universe