arXiv · 2201.12374
On the Kolmogorov Complexity of Binary Classifiers
Abstract
We provide tight upper and lower bounds on the expected minimum Kolmogorov complexity of binary classifiers that are consistent with labeled samples. The expected size is not more than complexity of the target concept plus the conditional entropy of the labels given the sample.
Explore related subjects
Keep this discovery
Samuel Epstein. 2022-01-28. On the Kolmogorov Complexity of Binary Classifiers. https://arxiv.org/abs/2201.12374
Cite the original work for its findings. Save a collection to share your selection of sources.