stat.MLOct 29, 2026

The Geometry of Multitask Learning: Sharp Rates for Shared Subspace Estimation

Authors: Tony Cai, Abhinav Chakraborty, Samory Kpotufe

Organizations: Department of Statistics and Data Science, University of Pennsylvania · Department of Statistics, Columbia University

Abstract

Learning a shared subspace in multitask learning is an important statistical problem, yet exact rates remain poorly understood in many of the formal settings considered in the literature. To address this gap, which arises from limitations of existing upper-bound techniques, we propose a general multitask lemma. The lemma provides sufficient conditions for fast subspace estimation in generic multitask settings, in the form of geometric conditions on the task regression functions and their estimators. We subsequently show that the multitask lemma yields sharp minimax rates---previously unknown---for linear regression and classification in the regimes considered, and rates matching up to logarithmic factors for additive-noise regression.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation

    May 1, 2026Shihong Ding, Fangyu Du, Cong FangShared Representation LearningRepresentation Learning

  2. SMART: A Spectral Transfer Approach to Multi-Task Learning

    Apr 22, 2026Boxin Zhao, Mladen Kolar, Jinchi LvMulti-Task LearningTransfer Learning