On Gaussian Mixture Models

Farzad Aryan

Primary Area: learning theory

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: GMM, Machin learning

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: Sample complexity of GMM

Abstract: We investigate the sample complexity of Gaussian mixture models (GMMs). Our results provide the optimal upper bound, in the context of uniform spherical Gaussian mixtures. Furthermore, we highlight the relationship between the sample complexity of GMMs and the distribution of spacings among their means.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5533