
-
BREEDS: Benchmarks for Subpopulation Shift
We develop a methodology for assessing the robustness of models to subpo...
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...
read it
-
From ImageNet to Image Classification: Contextualizing Progress on Benchmarks
Building rich machine learning datasets in a scalable manner often neces...
read it
-
Identifying Statistical Bias in Dataset Replication
Dataset replication is a useful tool for assessing whether improvements ...
read it
-
Image Synthesis with a Single (Robust) Classifier
We show that the basic classification framework alone can be used to tac...
read it
-
Computer Vision with a Single (Robust) Classifier
We show that the basic classification framework alone can be used to tac...
read it
-
Learning Perceptually-Aligned Representations via Adversarial Robustness
Many applications of machine learning require models that are human-alig...
read it
-
Adversarial Examples Are Not Bugs, They Are Features
Adversarial examples have attracted significant attention in machine lea...
read it
-
Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?
We study how the behavior of deep policy gradient algorithms reflects th...
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...
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...
read it
-
Adversarially Robust Generalization Requires More Data
Machine learning models are often susceptible to adversarial perturbatio...
read it
-
A Classification-Based Perspective on GAN Distributions
A fundamental, and still largely unanswered, question in the context of ...
read it
-
Generative Compression
Traditional image and video compression algorithms rely on hand-crafted ...
read it
-
Toward Streaming Synapse Detection with Compositional ConvNets
Connectomics is an emerging field in neuroscience that aims to reconstru...
read it
-
Deep Tensor Convolution on Multicores
Deep convolutional neural networks (ConvNets) of 3-dimensional kernels a...
read it