activity
20172022
most citedImplementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO

139 citations · 308 across the 8 of their papers we have counts for

collaborators
Showing stat.MLShow all

6 papers · 1 filter

stat.ML20208 cited

Identifying Statistical Bias in Dataset Replication

Logan Engstrom, Andrew Ilyas, Shibani Santurkar +3

Dataset replication is a useful tool for assessing whether improvements in test accuracy on a specific benchmark correspond to improvements in models' ability to generalize reliabl…

stat.ML2019

Adversarial Robustness as a Prior for Learned Representations

Logan Engstrom, Andrew Ilyas, Shibani Santurkar +3

An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings…

stat.ML2019

Adversarial Examples Are Not Bugs, They Are Features

Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras +3

Adversarial examples have attracted significant attention in machine learning, but the reasons for their existence and pervasiveness remain unclear. We demonstrate that adversarial…

stat.ML2018

Evaluating and Understanding the Robustness of Adversarial Logit Pairing

Logan Engstrom, Andrew Ilyas, Anish Athalye

We evaluate the robustness of Adversarial Logit Pairing, a recently proposed defense against adversarial examples. We find that a network trained with Adversarial Logit Pairing ach…

stat.ML2018

Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors

Andrew Ilyas, Logan Engstrom, Aleksander Madry

We study the problem of generating adversarial examples in a black-box setting in which only loss-oracle access to a model is available. We introduce a framework that conceptually…

stat.ML2018

How Does Batch Normalization Help Optimization?

Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas +1

Batch Normalization (BatchNorm) is a widely adopted technique that enables faster and more stable training of deep neural networks (DNNs). Despite its pervasiveness, the exact reas…