James Lucas

Theoretical bounds on estimation error for meta-learning

2020 · arXiv (Cornell University)

Machine learning models have traditionally been developed under the assumption that the training and test distributions match exactly. However, recent success in few-shot learning and related problems are encouraging signs that these models can be …

How Much More Data Do I Need? Estimating Requirements for Downstream Tasks

2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Given a small training data set and a learning algorithm, how much more data is necessary to reach a target validation or test performance? This question is of critical importance in applications such as autonomous …