Contaminated Multi-task Learning with Heterogeneity: Fundamental Limits and Optimal Algorithms
Ye Tian, Mengchu Li, Marco Avella Medina
stat.ML, cs.LG, math.ST, stat.ME
Submitted: 2026-07-02
Comments: 91 pages, 1 figure, 10 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- High-Dimensional Robust Mean Estimation with Untrusted Batches
- Robust Sparse Mean Estimation via Sum of Squares
- Distance-based and continuum Fano inequalities with applications to statistical estimation
- Adaptive and Robust Multi-Task Learning
- Optimal Cox regression under federated differential privacy: coefficients and cumulative hazards
- Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety
- Federated Transfer Learning with Differential Privacy
- Robust regression with covariate filtering: Heavy tails and adversarial contamination
- Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness
- Robust Unsupervised Multi-task and Transfer Learning on Gaussian Mixture Models
- Robust Data Fusion via Subsampling
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey