The goal of data attribution is to trace model predictions back to train...
We study the problem of (learning) algorithm comparison, where the goal ...
In the classical setting of self-selection, the goal is to learn k model...
We provide efficient estimation methods for first- and second-price auct...
We present a conceptual framework, datamodeling, for analyzing the behav...
We assess the tendency of state-of-the-art object recognition models to
...
We study the roots of algorithmic progress in deep policy gradient algor...
Building rich machine learning datasets in a scalable manner often
neces...
Dataset replication is a useful tool for assessing whether improvements ...
We show that the basic classification framework alone can be used to tac...
We show that the basic classification framework alone can be used to tac...
Many applications of machine learning require models that are human-alig...
Adversarial examples have attracted significant attention in machine
lea...
We study how the behavior of deep policy gradient algorithms reflects th...
We evaluate the robustness of Adversarial Logit Pairing, a recently prop...
We introduce a framework that unifies the existing work on black-box
adv...
Batch Normalization (BatchNorm) is a widely adopted technique that enabl...
Current neural network-based classifiers are susceptible to adversarial
...
Deep neural networks are demonstrating excellent performance on several
...
Current neural network-based image classifiers are susceptible to advers...
We address the issue of limit cycling behavior in training Generative
Ad...
Many database columns contain string or numerical data that conforms to ...
Neural network-based classifiers parallel or exceed human-level accuracy...