Amir Yehudayoff

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 …

Average-Case Information Complexity of Learning

2018 · arXiv (Cornell University)

How many bits of information are revealed by a learning algorithm for a concept class of VC-dimension $d$? Previous works have shown that even for $d=1$ the amount of information may be unbounded (tend to …

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 …