AIConfPaper
← Search

Aleksander Mądry

2 accepted papers

2023

A Data-Based Perspective on Transfer Learning

Saachi Jain, Hadi Salman, Alaa Khaddaj, Eric Wong, Sung Min Park, Aleksander Mądry
CVPR 2023poster

It is commonly believed that more pre-training data leads to better transfer learning performance. However, recent evidence suggests that removing data from the source dataset can actually help too. In this work, we present a framework for probing the impact of the source dataset's composition on tr…

Cited by 48Source ↗PDF ↗code ↗Scholar ↗
2023

FFCV: Accelerating Training by Removing Data Bottlenecks

Guillaume Leclerc, Andrew Ilyas, Logan Engstrom, Sung Min Park, Hadi Salman, Aleksander Mądry
CVPR 2023poster

We present FFCV, a library for easy, fast, resource-efficient training of machine learning models. FFCV speeds up model training by eliminating (often subtle) data bottlenecks from the training process. In particular, we combine techniques such as an efficient file storage format, caching, data pre-…

Cited by 84Source ↗PDF ↗code ↗Scholar ↗