AI RESEARCH
SMART: A Spectral Transfer Approach to Multi-Task Learning
arXiv CS.LG
•
ArXi:2604.20161v1 Announce Type: new Multi-task learning is effective for related applications, but its performance can deteriorate when the target sample size is small. Transfer learning can borrow strength from related studies; yet, many existing methods rely on restrictive bounded-difference assumptions between the source and target models.