← Search

Marvin Mengxin Zhang

2 accepted papers

2022

MEMO: Test Time Robustness via Adaptation and Augmentation

NeurIPS 2022accept

While deep neural networks can attain good accuracy on in-distribution test points, many applications require robustness even in the face of unexpected perturbations in the input, changes in the domain, or other sources of distribution shift. We study the problem of test time robustification, i.e.,…

2021

Adaptive Risk Minimization: Learning to Adapt to Domain Shift

NeurIPS 2021poster

A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violated in almost all practical applications: machine learning systems are regularly tested under distribution shift, due to c…