activity
20182020
most citedImplementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO

139 citations · 267 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CV202059 cited

Noise or Signal: The Role of Image Backgrounds in Object Recognition

Kai Xiao, Logan Engstrom, Andrew Ilyas +1

We assess the tendency of state-of-the-art object recognition models to depend on signals from image backgrounds. We create a toolkit for disentangling foreground and background si…

cs.LG2020139 cited

Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO

Logan Engstrom, Andrew Ilyas, Shibani Santurkar +4

We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms: Proximal Policy Optimization (PPO) and Trust Region Po…

cs.CV202061 cited

From ImageNet to Image Classification: Contextualizing Progress on Benchmarks

Dimitris Tsipras, Shibani Santurkar, Logan Engstrom +2

Building rich machine learning datasets in a scalable manner often necessitates a crowd-sourced data collection pipeline. In this work, we use human studies to investigate the cons…

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…

cs.CV2019

Image Synthesis with a Single (Robust) Classifier

Shibani Santurkar, Dimitris Tsipras, Brandon Tran +3

We show that the basic classification framework alone can be used to tackle some of the most challenging tasks in image synthesis. In contrast to other state-of-the-art approaches,…

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…