In this work we solve the problem of robustly learning a high-dimensional Gaussian mixture model with $k$ components from $\epsilon$-corrupted samples up to accuracy $\widetilde{O}(\epsilon)$ in total variation distance for any constant $k$ and with mild assumptions on the mixture. This robustness guarantee is optimal up to polylogarithmic factors. At the heart of our algorithm is a new way to relax a system of polynomial equations which corresponds to solving an improper learning problem where we are allowed to output a Gaussian mixture model whose weights are low-degree polynomials.
翻译:在这项工作中,我们解决了强力学习高斯高斯高斯高维混合物模型的问题,该模型的元件来自$-epsilon$-corptid 样本,其元件来自$-cropped 样本,其精确度为$-Uplete{O}(\\epsilon)$,任何恒定的美元总变差距离为$-Uplete{O}( ⁇ )$-Epslon),且该混合物的假设是温和的。这种稳健性保证与多元性因素相比是最佳的。我们算法的核心是放松多元性方程的新方法,它与解决一个不适当的学习问题相对应,即允许我们输出一个重量为低度多元性高斯混合的混合物模型。