TL;DR本文首次给出了一个多项式时间算法,用于在示例和标签中对抗性堕落下执行线性或多项式回归,并基于 SoS 方法提出了一种自然的凸松弛方法来解决非凸优化问题。
Abstract
We give the first polynomial-time algorithm for performing linear or
polynomial regression resilient to adversarial corruptions in both examples and
labels.
Given a sufficiently large (polynomial-size) training set drawn i.i.d. from
distribution D and subsequently corrupted on some fra