Robust supervised learning with coordinate gradient descent

DOI10.1007/s11222-023-10283-7zbMath1517.62038arXiv2201.13372OpenAlexW4385463474MaRDI QIDQ6172182

Ibrahim Merad, Stéphane Gaïffas

Publication date: 16 August 2023

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.13372

zbMATH Keywords

outliersgeneralization errorrobust methodscoordinate gradient descentheavy-tailed datarobust gradient descent

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Robustness and adaptive procedures (parametric inference) (62F35) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Geometric median and robust estimation in Banach spaces
• Block coordinate descent algorithms for large-scale sparse multiclass classification
• Sub-Gaussian mean estimators
• Risk bounds for statistical learning
• Empirical risk minimization for heavy-tailed losses
• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Random generation of combinatorial structures from a uniform distribution
• The space complexity of approximating the frequency moments
• Introductory lectures on convex optimization. A basic course.
• Sub-Gaussian estimators of the mean of a random vector
• Robust covariance and scatter matrix estimation under Huber's contamination model
• The ``automatic robustness of minimum distance functionals
• On depth and deep points: A calculus.
• Challenging the empirical mean and empirical variance: a deviation study
• Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
• A generalized Catoni's M-estimator under finite \(\alpha\)-th moment assumption with \(\alpha \in (1,2)\)
• Robust sub-Gaussian estimation of a mean vector in nearly linear time
• Robust machine learning by median-of-means: theory and practice
• Mean estimation with sub-Gaussian rates in polynomial time
• Robust classification via MOM minimization
• Robust regression via mutivariate regression depth
• Efficient learning with robust gradient descent
• Mean estimation and regression under heavy-tailed distributions: A survey
• Coordinate descent algorithms
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Coordinate descent algorithms for lasso penalized regression
• Minimization of functions having Lipschitz continuous first partial derivatives
• Local Rademacher complexities
• Robust multivariate mean estimation: the optimality of trimmed mean
• Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems
• Robust principal component analysis?
• Learning Halfspaces with Malicious Noise
• Asymptotic Statistics
• The multivariate L ₁ -median and associated data depth
• On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization
• Robust Estimators in High-Dimensions Without the Computational Intractability
• Learning from untrusted data
• Robust Estimation via Robust Gradient Estimation
• Efficient Algorithms and Lower Bounds for Robust Linear Regression
• Bandits With Heavy Tail
• On the Convergence of Block Coordinate Descent Type Methods
• Model Selection and Estimation in Regression with Grouped Variables
• Robust Estimation of a Location Parameter
• A General Qualitative Definition of Robustness
• The 1972 Wald Lecture Robust Statistics: A Review
• Analysis of Extreme Values
• Robust Statistics
• Sparse recovery by reduced variance stochastic approximation

This page was built for publication: Robust supervised learning with coordinate gradient descent