Optimal L2 Regularization in High-dimensional Continual Linear Regression

ArXi:2601.13844v2 Announce Type: replace We study generalization in an overparameterized continual linear regression setting, where a model is trained with L2 (isotropic) regularization across a sequence of tasks. We derive a closed-form expression for the expected generalization loss in the high-dimensional regime that holds for arbitrary linear teachers. We nstrate that isotropic regularization mitigates label noise under both single-teacher and multiple i.i.d.