Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise

We study the problem of learning general (i.e., not necessarily homogeneous) halfspaces with Random Classification Noise under the Gaussian distribution. We establish nearly-matching algorithmic and Statistical Query (SQ) lower bound results revealing a surprising information-computation gap for this basic problem. Specifically, the sample complexity of this learning problem is widetildeTheta(d/ε), where d is the dimension and ε is the excess error. Our positive result is a computationally efficient learning algorithm with sample complexity tildeO(d/ε + d/(maxp, ε)2), where p quantifies the bias of the target halfspace. On the lower bound side, we show that any efficient SQ algorithm (or low-degree test) for the problem requires sample complexity at least Omega(d1/2/(maxp, ε)2). Our lower bound suggests that this quadratic dependence on 1/ε is inherent for efficient algorithms.