Shibani Santurkar

is this you? claim profile

0 followers
MIT

BREEDS: Benchmarks for Subpopulation Shift

We develop a methodology for assessing the robustness of models to subpo...
08/11/2020 ∙ by Shibani Santurkar, et al. ∙ 5 ∙ share

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

We study the roots of algorithmic progress in deep policy gradient algor...
05/25/2020 ∙ by Logan Engstrom, et al. ∙ 0 ∙ share

read it
From ImageNet to Image Classification: Contextualizing Progress on Benchmarks

Building rich machine learning datasets in a scalable manner often neces...
05/22/2020 ∙ by Dimitris Tsipras, et al. ∙ 24 ∙ share

read it
Identifying Statistical Bias in Dataset Replication

Dataset replication is a useful tool for assessing whether improvements ...
05/19/2020 ∙ by Logan Engstrom, et al. ∙ 10 ∙ share

read it
Image Synthesis with a Single (Robust) Classifier

We show that the basic classification framework alone can be used to tac...
06/06/2019 ∙ by Shibani Santurkar, et al. ∙ 0 ∙ share

read it
Computer Vision with a Single (Robust) Classifier

We show that the basic classification framework alone can be used to tac...
06/06/2019 ∙ by Shibani Santurkar, et al. ∙ 0 ∙ share

read it
Learning Perceptually-Aligned Representations via Adversarial Robustness

Many applications of machine learning require models that are human-alig...
06/03/2019 ∙ by Logan Engstrom, et al. ∙ 0 ∙ share

read it
Adversarial Examples Are Not Bugs, They Are Features

Adversarial examples have attracted significant attention in machine lea...
05/06/2019 ∙ by Andrew Ilyas, et al. ∙ 0 ∙ share

read it
Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?

We study how the behavior of deep policy gradient algorithms reflects th...
11/06/2018 ∙ by Andrew Ilyas, et al. ∙ 4 ∙ share

read it
There Is No Free Lunch In Adversarial Robustness (But There Are Unexpected Benefits)

We provide a new understanding of the fundamental nature of adversariall...
05/30/2018 ∙ by Dimitris Tsipras, et al. ∙ 2 ∙ share

read it
How Does Batch Normalization Help Optimization? (No, It Is Not About Internal Covariate Shift)

Batch Normalization (BatchNorm) is a widely adopted technique that enabl...
05/29/2018 ∙ by Shibani Santurkar, et al. ∙ 0 ∙ share

read it
Adversarially Robust Generalization Requires More Data

Machine learning models are often susceptible to adversarial perturbatio...
04/30/2018 ∙ by Ludwig Schmidt, et al. ∙ 0 ∙ share

read it
A Classification-Based Perspective on GAN Distributions

A fundamental, and still largely unanswered, question in the context of ...
11/02/2017 ∙ by Shibani Santurkar, et al. ∙ 0 ∙ share

read it
Generative Compression

Traditional image and video compression algorithms rely on hand-crafted ...
03/04/2017 ∙ by Shibani Santurkar, et al. ∙ 0 ∙ share

read it
Toward Streaming Synapse Detection with Compositional ConvNets

Connectomics is an emerging field in neuroscience that aims to reconstru...
02/23/2017 ∙ by Shibani Santurkar, et al. ∙ 0 ∙ share

read it
Deep Tensor Convolution on Multicores

Deep convolutional neural networks (ConvNets) of 3-dimensional kernels a...
11/20/2016 ∙ by David Budden, et al. ∙ 0 ∙ share

read it

Shibani Santurkar

Featured Co-authors

Aleksander Madry

Kunal Talwar

Jacob Steinhardt

David Budden

Andrew Ilyas

Dimitris Tsipras

Logan Engstrom

Ludwig Schmidt

Nir Shavit

Brandon Tran

Yaron Meirovitch

BREEDS: Benchmarks for Subpopulation Shift

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

From ImageNet to Image Classification: Contextualizing Progress on Benchmarks

Identifying Statistical Bias in Dataset Replication

Image Synthesis with a Single (Robust) Classifier

Computer Vision with a Single (Robust) Classifier

Learning Perceptually-Aligned Representations via Adversarial Robustness

Adversarial Examples Are Not Bugs, They Are Features

Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?

There Is No Free Lunch In Adversarial Robustness (But There Are Unexpected Benefits)

How Does Batch Normalization Help Optimization? (No, It Is Not About Internal Covariate Shift)

Adversarially Robust Generalization Requires More Data

A Classification-Based Perspective on GAN Distributions

Generative Compression

Toward Streaming Synapse Detection with Compositional ConvNets

Deep Tensor Convolution on Multicores