Online Generalized Sparse Regression: How Does Overparametrization Help?
Read the original on arXiv Machine Learning →The paper introduces an online generalized-sparsity-constrained regression framework that addresses key challenges in online sparse regression, such as dynamic regularization, memory usage, and real-time computation. It proposes an efficient online hard‑thresholding algorithm that performs closed‑form updates using only summary statistics, achieving global convergence at optimal statistical rates when the projection set is overparameterized. Numerical experiments show the method consistently outperforms existing alternatives in online cardinality‑constrained linear regression and low‑rank matrix sensing.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.