Statistical Learning
Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
The bound is based on a novel parametric form of the Chebyshev-Cantelli inequality (a.k.a.
Out-of-Distribution Generalization in Kernel Regression
In real word applications, the data generating process for training a machine learning model often differs from what the model encounters in the test stage.
Adapting to Misspecification in Contextual Bandits
However, they left the adapting to unknown ฮต as an open question.
Coresets for Robust Training of Neural Networks against Noisy Labels
There has been a great empirical progress in robust training of neural networks against noisy labels.
Learning with Labeling Induced Abstentions
We assume this system has a limited budget for requesting ground-truth labels (e.g. from a
