5,337
edits
Line 622: | Line 622: | ||
==Adversarial Robustness== | ==Adversarial Robustness== | ||
Beginning of Lecture 8 (Sept. 24 2020) | |||
In standard ERM, we have a dataset: | |||
<math>\{(x_i, y_i)\}_{i=1}^{n}</math> where <math>x_i \in \mathbb{R}^d</math> and <math>y_i \in [c]</math> | |||
We optimize <math>\min_{\theta} E \left[ l(f_{\theta}(x), y) \right] = \frac{1}{n} \sum l(f_{\theta}(x_i), y_i) </math> | |||
==Misc== | ==Misc== |