Optimal L2 Regularization in High-dimensional Continual Linear Regression

arXiv:2601.13844v2 Announce Type: replace Abstract: 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 demonstrate that isotropic regularization mitigates label noise under both single-teacher and multiple i.i.d. teacher settings, whereas prior work accommodating multiple teachers either did not employ regularization or used memory-demanding methods. Furthermore, we prove that the optimal fixed regularization strength scales nearly linearly with the number of tasks T, specifically as T/ln T. To our knowledge, this is the first such result in theoretical continual learning. Finally, we validate our theoretical findings through experiments on linear regression and neural networks, illustrating how this scaling law affects generalization and offering a practical recipe for the design of continual learning systems.

Related

• Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimal
• Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
• Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification

Source: arXiv cs.LG | 2026-04-14