Sara Hooker

TL;DR: It is shown that unstructured sparse architectures learned through pruning cannot be trained from scratch to the same test set performance as a model trained with joint sparsification and optimization, and the need for large-scale benchmarks in the field of model compression is highlighted.

TL;DR: This work uses a simple and common pre-processing step ---adding a constant shift to the input data--- to show that a transformation with no effect on the model can cause numerous methods to incorrectly attribute.

TL;DR: In this paper, an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks is proposed, and it is shown that ensemble based approaches outperform a random assignment of importance.

TL;DR: This report suggests various steps that different stakeholders can take to improve the verifiability of claims made about AI systems and their associated development processes, with a focus on providing evidence about the safety, security, fairness, and privacy protection of AI systems.

TL;DR: In this article, a simple and common pre-processing step, adding a constant shift to the input data, is used to show that a transformation with no effect on the model can cause numerous methods to incorrectly attribute.