
We present a polynomial-time algorithm that robustly learns the class of degree-d polynomial threshold functions under the Gaussian distribution in the presence of a constant fraction of adversarial corruptions, achieving error Oc,d(1) opt^(1-c) for any constant c > 0, where opt is the fraction of corruptions.


coremsg

efficient-robust-learning-of-low-degree-polynomial-threshold-functions-under-adversarial-corruptions


Efficient Robust Learning of Low-Degree Polynomial Threshold Functions under Adversarial Corruptions
