Adaptive and robust multi-task learning

DOI10.1214/23-AOS2319arXiv2202.05250MaRDI QIDQ6183769FDOQ6183769

Authors: Yaqi Duan, Kaizheng Wang 

Publication date: 4 January 2024

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: We study the multi-task learning problem that aims to simultaneously analyze multiple datasets collected from different sources and learn one model for each of them. We propose a family of adaptive methods that automatically utilize possible similarities among those tasks while carefully handling their differences. We derive sharp statistical guarantees for the methods and prove their robustness against outlier tasks. Numerical experiments on synthetic and real datasets demonstrate the efficacy of our new methods.

Full work available at URL: https://arxiv.org/abs/2202.05250

Recommendations

• Decision Learning and Adaptation Over Multi-Task Networks
• Adaptive multitask network based on maximum correntropy learning algorithm
• Learning multiple tasks with kernel methods
• Online Multitask Learning
• Multiplicative multitask feature learning
• Multi-task learning via linear functional strategy

zbMATH Keywords

clusteringmodel misspecificationrobustnessadaptivitymultitask learninglow-rank model

Mathematics Subject Classification ID

Point estimation (62F10) Statistical aspects of big data and data science (62R07)

Cites Work

• Ideal spatial adaptation by wavelet shrinkage
• Title not available (Why is that?)
• Estimation of the mean of a multivariate normal distribution
• Title not available (Why is that?)
• Sparsity and Smoothness Via the Fused Lasso
• Robust Estimation of a Location Parameter
• Robust Statistics
• A no-free-lunch theorem for multitask learning
• Data enriched linear regression
• Fused Lasso approach in regression coefficients clustering -- learning parameter heterogeneity in data integration
• Title not available (Why is that?)
• A tail inequality for quadratic forms of subgaussian random vectors
• Estimation with quadratic loss.
• Title not available (Why is that?)
• The use of Previous Experience in Reaching Statistical Decisions
• Oracle inequalities and optimal inference under group sparsity
• Parametric robustness: Small biases can be worthwhile
• Homogeneity pursuit
• Grouping pursuit through a regularization solution surface
• Robust PCA via Outlier Pursuit
• Limiting the Risk of Bayes and Empirical Bayes Estimators--Part II: The Empirical Bayes Case
• Two proposals for robust PCA using semidefinite programming
• Title not available (Why is that?)
• Stein's Estimation Rule and Its Competitors--An Empirical Bayes Approach
• Learning Theory and Kernel Machines
• High dimensional robust M-estimation: asymptotic variance via approximate message passing
• Convex multi-task feature learning
• Support union recovery in high-dimensional multivariate regression
• Wavelet methods in statistics: some recent developments and their applications
• Title not available (Why is that?)
• Title not available (Why is that?)
• On nonparametric confidence intervals
• Outlier detection using nonconvex penalized regression
• On a Problem of Adaptive Estimation in Gaussian White Noise
• Learning multiple tasks with kernel methods
• Trace norm regularization: reformulations, algorithms, and multi-task learning
• New perspectives on \(k\)-support and cluster norms
• Computer age statistical inference. Algorithms, evidence, and data science
• Multidimensional linear functional estimation in sparse Gaussian models and robust estimation of the mean
• The landscape of empirical risk for nonconvex losses
• A Dirty Model for Multiple Sparse Regression
• The benefit of multitask representation learning
• Individual Data Protected Integrative Regression Analysis of High-Dimensional Heterogeneous Data

Cited In (3)

• Decision Learning and Adaptation Over Multi-Task Networks
• Adaptive multitask network based on maximum correntropy learning algorithm
• Multi-task learning via linear functional strategy

This page was built for publication: Adaptive and robust multi-task learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6183769)