Convex and non-convex approaches for statistical inference with class-conditional noisy labels

MaRDI QIDQ5148952zbMATH OpenFDO

Authors Hyebin Song, Ran Dai, Garvesh Raskutti, Rina Foygel Barber

Publication date 5 February 2021

Full work available at URL https://arxiv.org/abs/1910.02348, https://jmlr.csail.mit.edu/papers/v21/19-833.html

zbMATH Keywords

generalized linear modelregularizationnon-convexityPU-learningclass-conditional label noise

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Classification with asymmetric label noise: consistency and maximal denoising
• On the noise estimation statistics
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
• scientific article; zbMATH DE number 6982911
• Harmless label noise and informative soft-labels in supervised classification

Cites work

• scientific article; zbMATH DE number 47310 (Why is no real title available?)
• scientific article; zbMATH DE number 6982911 (Why is no real title available?)
• A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers
• An Optimum Property of Regular Maximum Likelihood Estimation
• Asymptotic Statistics
• Asymptotics for Lasso-type estimators.
• Bias and efficiency loss due to misclassified responses in binary regression
• Boosting in the presence of outliers: adaptive classification with nonconvex loss functions
• Efficiency of estimating equations and the use of pivots
• First-order methods in optimization
• High-dimensional inference: confidence intervals, \(p\)-values and R-software \texttt{hdi}
• High-dimensional probability. An introduction with applications in data science
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
• Inference using surrogate outcome data and a validation sample
• Mathematical Statistics
• Measurement Error in Nonlinear Models
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over \ell_q-Balls
• Misclassification of the dependent variable in a discrete-response setting
• Modeling Discrete Choice With Response Error: Food Stamp Participation
• Multivariate statistical modelling based on generalized linear models.
• On asymptotically optimal confidence regions and tests for high-dimensional models
• PUlasso: High-Dimensional Variable Selection With Presence-Only Data
• Presence‐Only Data and the EM Algorithm
• Randomized Response, Statistical Disclosure Control and Misclassificatio: a Review
• Regularized \(M\)-estimators with nonconvexity: statistical and algorithmic theory for local optima
• Robust Stochastic Approximation Approach to Stochastic Programming
• Statistical consistency and asymptotic normality for high-dimensional robust \(M\)-estimators
• The landscape of empirical risk for nonconvex losses

Cited in

(4)

• Harmless label noise and informative soft-labels in supervised classification
• Label distribution learning with noisy labels via three-way decisions
• Classification with asymmetric label noise: consistency and maximal denoising
• Lasso penalization for high-dimensional beta regression models: computation, analysis, and inference

This page was built for publication: Convex and non-convex approaches for statistical inference with class-conditional noisy labels

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5148952)