500 citations · 2.2k across the 35 of their papers we have counts for
6 papers · 1 filter
Editing a classifier by rewriting its prediction rules
Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango +3
We present a methodology for modifying the behavior of a classifier by directly rewriting its prediction rules. Our approach requires virtually no additional data collection and ca…
Leveraging Sparse Linear Layers for Debuggable Deep Networks
Eric Wong, Shibani Santurkar, Aleksander Mądry
We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. These networks remain highly accurate while also bei…
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…
A Closer Look at Deep Policy Gradients
Andrew Ilyas, Logan Engstrom, Shibani Santurkar +4
We study how the behavior of deep policy gradient algorithms reflects the conceptual framework motivating their development. To this end, we propose a fine-grained analysis of stat…
Adversarially Robust Generalization Requires More Data
Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras +2
Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" acc…
A Classification-Based Study of Covariate Shift in GAN Distributions
Shibani Santurkar, Ludwig Schmidt, Aleksander Mądry
A basic, and still largely unanswered, question in the context of Generative Adversarial Networks (GANs) is whether they are truly able to capture all the fundamental characteristi…