Review for NeurIPS paper: Transfer Learning via \ell_1 Regularization

While the presented model can be posed as a transfer learning problem. This paper is more about concept drift. Therefore, the title Transfer learning via l1 Regularization is a bit too broad and can be misleading for some readers. However, Lasso is not considered as a state-of-the-art (SOTA) for concept drift and transfer learning. Lasso is designed for neither of these problem. On the other hand, there are many other methods for concept drift and transfer learning, with some discussed in the Related Work section but none is compared against in the experiment.