Under label corruptions, we prove that this simple estimator achieves minimax near-optimal riskonawiderange ofgeneralized linear models, including Gaussian regression, Poisson regression and Binomial regression.

Consider ascenario inwhich data items are being generated one by one, e.g., IP traffic monitoring or web searches.

Our second algorithm offers a tail-sensitive bound that could be much better on skewed data. The corresponding algorithms are also simple and efficient.