Shay Moran

On statistical learning via the lens of compression

2016 · arXiv (Cornell University)

This work continues the study of the relationship between sample compression schemes and statistical learning, which has been mostly investigated within the framework of binary classification. The central theme of this work is establishing equivalences …

Towards a Unified Information-Theoretic Framework for Generalization

2021 · arXiv (Cornell University)

In this work, we investigate the expressiveness of the conditional mutual information (CMI) framework of Steinke and Zakynthinou (2020) and the prospect of using it to provide a unified framework for proving generalization bounds in …

Active Learning with Label Comparisons

2022 · arXiv (Cornell University)

Supervised learning typically relies on manual annotation of the true labels. When there are many potential classes, searching for the best one can be prohibitive for a human annotator. On the other hand, comparing two …

Learning-Augmented Algorithms with Explicit Predictors

2024 · arXiv (Cornell University)

Recent advances in algorithmic design show how to utilize predictions obtained by machine learning models from past and present data. These approaches have demonstrated an enhancement in performance when the predictions are accurate, while also …

Dual VC Dimension Obstructs Sample Compression by Embeddings

2024 · arXiv (Cornell University)

This work studies embedding of arbitrary VC classes in well-behaved VC classes, focusing particularly on extremal classes. Our main result expresses an impossibility: such embeddings necessarily require a significant increase in dimension. In particular, we …

Of Dice and Games: A Theory of Generalized Boosting

2024 · arXiv (Cornell University)

Cost-sensitive loss functions are crucial in many real-world prediction problems, where different types of errors are penalized differently; for example, in medical diagnosis, a false negative prediction can lead to worse consequences than a false …