AI RESEARCH
Residual-as-Teacher: Mitigating Bias Propagation in Student--Teacher Estimation
arXiv CS.LG
•
ArXi:2603.25466v1 Announce Type: cross We study statistical estimation in a student--teacher setting, where predictions from a pre-trained teacher are used to guide a student model. A standard approach is to train the student to directly match the teacher's outputs, which we refer to as student soft matching (SM). This approach directly propagates any systematic bias or mis-specification present in the teacher, thereby degrading the student's predictions.