Distributionally robust optimization: A review
H Rahimian, S Mehrotra - arXiv preprint arXiv:1908.05659, 2019 - arxiv.org
The concepts of risk-aversion, chance-constrained optimization, and robust optimization
have developed significantly over the last decade. Statistical learning community has also …
have developed significantly over the last decade. Statistical learning community has also …
Computational optimal transport: With applications to data science
Optimal transport (OT) theory can be informally described using the words of the French
mathematician Gaspard Monge (1746–1818): A worker with a shovel in hand has to move a …
mathematician Gaspard Monge (1746–1818): A worker with a shovel in hand has to move a …
Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization
Overparameterized neural networks can be highly accurate on average on an iid test set yet
consistently fail on atypical groups of the data (eg, by learning spurious correlations that …
consistently fail on atypical groups of the data (eg, by learning spurious correlations that …
On gradient descent ascent for nonconvex-concave minimax problems
We consider nonconvex-concave minimax problems, $\min_ {\mathbf {x}}\max_ {\mathbf
{y}\in\mathcal {Y}} f (\mathbf {x},\mathbf {y}) $, where $ f $ is nonconvex in $\mathbf {x} $ but …
{y}\in\mathcal {Y}} f (\mathbf {x},\mathbf {y}) $, where $ f $ is nonconvex in $\mathbf {x} $ but …
Wasserstein distributionally robust optimization: Theory and applications in machine learning
Many decision problems in science, engineering, and economics are affected by uncertain
parameters whose distribution is only indirectly observable through samples. The goal of …
parameters whose distribution is only indirectly observable through samples. The goal of …
Certifying some distributional robustness with principled adversarial training
Neural networks are vulnerable to adversarial examples and researchers have proposed
many heuristic attack and defense mechanisms. We address this problem through the …
many heuristic attack and defense mechanisms. We address this problem through the …
Learning models with uniform performance via distributionally robust optimization
JC Duchi, H Namkoong - The Annals of Statistics, 2021 - projecteuclid.org
Learning models with uniform performance via distributionally robust optimization Page 1 The
Annals of Statistics 2021, Vol. 49, No. 3, 1378–1406 https://doi.org/10.1214/20-AOS2004 © …
Annals of Statistics 2021, Vol. 49, No. 3, 1378–1406 https://doi.org/10.1214/20-AOS2004 © …
Evaluating machine accuracy on imagenet
We evaluate a wide range of ImageNet models with five trained human labelers. In our year-
long experiment, trained humans first annotated 40,000 images from the ImageNet and …
long experiment, trained humans first annotated 40,000 images from the ImageNet and …
Understanding contrastive learning via distributionally robust optimization
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias,
wherein negative samples may encompass similar semantics (\eg labels). However, existing …
wherein negative samples may encompass similar semantics (\eg labels). However, existing …
Robust Wasserstein profile inference and applications to machine learning
We show that several machine learning estimators, including square-root least absolute
shrinkage and selection and regularized logistic regression, can be represented as …
shrinkage and selection and regularized logistic regression, can be represented as …