Developing simple, sample-efficient learning algorithms for robust classification is a pressing issue in today's tech-dominated world, and current theoretical techniques requiring exponential sample complexity and complicated improper learning rules fall far from answering the need. In this work we study the fundamental paradigm of (robust) $\textit{empirical risk minimization}$ (RERM), a simple process in which the learner outputs any hypothesis minimizing its training error. RERM famously fails to robustly learn VC classes (Montasser et al., 2019a), a bound we show extends even to `nice' settings such as (bounded) halfspaces. As such, we study a recent relaxation of the robust model called $\textit{tolerant}$ robust learning (Ashtiani et al., 2022) where the output classifier is compared to the best achievable error over slightly larger perturbation sets. We show that under geometric niceness conditions, a natural tolerant variant of RERM is indeed sufficient for $\gamma$-tolerant robust learning VC classes over $\mathbb{R}^d$, and requires only $\tilde{O}\left( \frac{VC(H)d\log \frac{D}{\gamma\delta}}{\epsilon^2}\right)$ samples for robustness regions of (maximum) diameter $D$.
翻译:用于稳健分类的简单、 抽样高效的学习算法是当今技术主宰世界的一个紧迫问题,而目前要求指数抽样复杂和复杂不适当学习规则的理论技术远不能满足需求。 在这项工作中,我们研究了(robust) $\ textit{经验风险最小化$(RERM) 的基本范式(RERM), 学习者在这一过程中输出任何假设,将其培训错误最小化。 RERM 以强健学习 VC 类( Montasser 等人, 2019a) 闻名失败, 我们展示了连齐的“ nice” 设置, 如( 约束的) 半空空间。 因此, 我们研究了所谓的“ $\ textitleit{ 容忍} $ 强健健的学习模式( Ashtiani et al. 2022) 的基本范式( ) 。 我们显示, 在几何友好条件下, RRM 的自然宽容变量对于 $\gamma- comstal learstead VC c$@\\\\\\\\\\\\\\\\\\\\\\\\\\\\ read real realest reality) $( rum) rum) ausyrety (time) a $ (tize) (time) (time) (time) (time) (time) (美元= $\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\