# Provable Robust Classification via Learned Smoothed Densities

9 May 2020Saeed SaremiRupesh Srivastava

Smoothing classifiers and probability density functions with Gaussian kernels appear unrelated, but in this work, they are unified for the problem of robust classification. The key building block is approximating the $\textit{energy function}$ of the random variable $Y=X+N(0,\sigma^2 I_d)$ with a neural network which we use to formulate the problem of robust classification in terms of $\widehat{x}(Y)$, the $\textit{Bayes estimator}$ of $X$ given the noisy measurements $Y$... (read more)

PDF Abstract

No code implementations yet. Submit your code now