Robust high dimensional learning for Lipschitz and convex losses

MaRDI QIDQ5149262FDO

Authors Chinot Geoffrey, Lecué Guillaume, Lerasle Matthieu

Publication date 8 February 2021

Full work available at URL https://arxiv.org/abs/1905.04281

zbMATH Keywords

total variationLassoSLOPEgroup Lassorobust learningLipschtiz and convex loss functionsRademacher complexity boundssparsity bounds

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Robust statistical learning with Lipschitz and convex loss functions
• Robust classification via MOM minimization
• Robust machine learning by median-of-means: theory and practice
• Learning under \((1 + \epsilon)\)-moment conditions
• Excess risk bounds in robust empirical risk minimization

Cites work

• scientific article; zbMATH DE number 6388313 (Why is no real title available?)
• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 845714 (Why is no real title available?)
• scientific article; zbMATH DE number 6253925 (Why is no real title available?)
• A fast unified algorithm for solving group-lasso penalize learning problems
• A new method for estimation and model selection: \(\rho\)-estimation
• An Iterative Regularization Method for Total Variation-Based Image Restoration
• Atomic Norm Denoising With Applications to Line Spectral Estimation
• Convexity, Classification, and Risk Bounds
• ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels
• Empirical minimization
• Estimating structured high-dimensional covariance and precision matrices: optimal rates and adaptive estimation
• Estimation and testing under sparsity. École d'Été de Probabilités de Saint-Flour XLV -- 2015
• Gaussian averages of interpolated bodies and applications to approximate reconstruction
• Interactions between compressed sensing random matrices and high dimensional geometry
• Living on the edge: phase transitions in convex programs with random data
• Local Rademacher complexities
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• On multiplier processes under weak moment assumptions
• On sparsity inducing regularization methods for machine learning
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Optimal aggregation of classifiers in statistical learning.
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Random generation of combinatorial structures from a uniform distribution
• Regularization and the small-ball method. I: Sparse recovery
• Regularization and the small-ball method. II: Complexity dependent error rates
• Robust linear least squares regression
• Robust low-rank matrix estimation
• SLOPE-adaptive variable selection via convex optimization
• Simultaneous analysis of Lasso and Dantzig selector
• Slope meets Lasso: improved oracle bounds and optimality
• Smooth discrimination analysis
• Sparsity and Smoothness Via the Fused Lasso
• Stabilité et instabilité du risque minimax pour des variables indépendantes équidistribuées
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Statistics for high-dimensional data. Methods, theory and applications.
• Structured sparsity through convex optimization
• Sub-Gaussian mean estimators
• The Group Lasso for Logistic Regression
• The space complexity of approximating the frequency moments
• Tikhonov Regularization and Total Least Squares
• Towards the study of least squares estimators with convex penalty
• Upper and lower bounds for stochastic processes. Modern methods and classical problems

Cited in

(6)

• Robust supervised learning with coordinate gradient descent
• Robust high dimensional learning for Lipschitz and convex losses
• Risk-Based Robust Statistical Learning by Stochastic Difference-of-Convex Value-Function Optimization
• Iteratively reweighted \(\ell_1\)-penalized robust regression
• Sparse additive support vector machines in bounded variation space
• Learning with risks based on M-location

Describes a project that uses

Uses Software

• gglasso

This page was built for publication: Robust high dimensional learning for Lipschitz and convex losses

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5149262)