Search Results for author:
Found 11 papers, 5 papers with code
Adversarially Robust Generalization Just Requires More Unlabeled Data
Neural network robustness has recently been highlighted by the existence of adversarial examples.
MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius
Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly.
Transferred Discrepancy: Quantifying the Difference Between Representations
Our experiments show that TD can provide fine-grained information for varied downstream tasks, and for the models trained from different initializations, the learned features are not the same in terms of downstream-task predictions.
Pretrain-to-Finetune Adversarial Training via Sample-wise Randomized Smoothing
For certification, we carefully allocate specific robust regions for each test sample.
DORO: Distributional and Outlier Robust Optimization
Many machine learning tasks involve subpopulation shift where the testing data distribution is a subpopulation of the training distribution.
Understanding Overfitting in Reweighting Algorithms for Worst-group Performance
Prior work has proposed various reweighting algorithms to improve the worst-group performance of machine learning models for fairness.
Boosted CVaR Classification
To learn such randomized classifiers, we propose the Boosted CVaR Classification framework which is motivated by a direct relationship between CVaR and a classical boosting algorithm called LPBoost.
Understanding Why Generalized Reweighting Does Not Improve Over ERM
Together, our results show that a broad category of what we term GRW approaches are not able to achieve distributionally robust generalization.
Predicting Out-of-Distribution Error with Confidence Optimal Transport
Out-of-distribution (OOD) data poses serious challenges in deployed machine learning models as even subtle changes could incur significant performance drops.
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
Recent work has built the connection between self-supervised learning and the approximation of the top eigenspace of a graph Laplacian operator, suggesting that learning a linear probe atop such representation can be connected to RKHS regression.
Spectrally Transformed Kernel Regression
Unlabeled data is a key component of modern machine learning.
