Abstract Machine learning brings the hope of finding new biomarkers extracted from cohorts with rich biomedical measurements. A good biomarker is one that gives reliable detection of …
A Subbaswamy, R Adams… - … conference on artificial …, 2021 - proceedings.mlr.press
As the use of machine learning in high impact domains becomes widespread, the importance of evaluating safety has increased. An important aspect of this is evaluating how …
J Wang, R Gao, Y Xie - arXiv preprint arXiv:2109.11926, 2021 - arxiv.org
We study distributionally robust optimization (DRO) with Sinkhorn distance--a variant of Wasserstein distance based on entropic regularization. We derive convex programming …
A Agarwal, T Zhang - Conference on Learning Theory, 2022 - proceedings.mlr.press
In this paper, we consider learning scenarios where the learned model is evaluated under an unknown test distribution which potentially differs from the training distribution (ie …
We review distributionally robust optimization (DRO), a principled approach for constructing statistical estimators that hedge against the impact of deviations in the expected loss …
M Li, H Namkoong, S Xia - Advances in Neural Information …, 2021 - proceedings.neurips.cc
The performance of ML models degrades when the training population is different from that seen under operation. Towards assessing distributional robustness, we study the worst-case …
H Kremer, Y Nemmour… - … on Machine Learning, 2023 - proceedings.mlr.press
Moment restrictions and their conditional counterparts emerge in many areas of machine learning and statistics ranging from causal inference to reinforcement learning. Estimators …
Several recent works have studied the societal effects of AI; these include issues such as fairness, robustness, and safety. In many of these objectives, a learner seeks to minimize its …
Wasserstein distributionally robust estimators have emerged as powerful models for prediction and decision-making under uncertainty. These estimators provide attractive …