Adversarial Examples Are Not Bugs, They Are Features

A new perspective on adversarial perturbations

A Closer Look at Deep Policy Gradients (Part 3: Landscapes and Trust Regions)

In the second part of our analysis, we examine gradient estimate quality and the value function as a variance reducing baseline.

A Closer Look at Deep Policy Gradients (Part 2: Gradients and Values)

In the second part of our analysis, we examine gradient estimate quality and the value function as a variance reducing baseline.

A Closer Look at Deep Policy Gradients (Part 1: Intro)

An introduction to policy gradient methods, kicking off our 3-part analysis.

How does Batch Normalization Help Optimization?

An closer look at one of the most popular techniques in modern deep learning.

Training Robust Classifiers (Part 2)

A robust optimization perspective on training robust models.

Training Robust Classifiers (Part 1)

A robust optimization perspective on training robust models.

A Brief Introduction to Adversarial Examples

ML classifiers tend to be a lot more brittle than we think.