# Theory of the GMM Kernel

arXiv: https://arxiv.org/abs/1608.00550 · HTML: https://mlsanity.com/paper/1608.00550/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2016.

## Built on by (most cited first, 2 of 2)

- [GCWSNet: Generalized Consistent Weighted Sampling for Scalable and Accurate Training of Neural Networks](https://mlsanity.com/paper/2201.02283/) (2022)
- [pGMM Kernel Regression and Comparisons with Boosted Trees](https://mlsanity.com/paper/2207.08667/) (2022)

## Abstract (arXiv)

We develop some theoretical results for a robust similarity measure named "generalized min-max" (GMM). This similarity has direct applications in machine learning as a positive definite kernel and can be efficiently computed via probabilistic hashing. Owing to the discrete nature, the hashed values can also be used for efficient near neighbor search. We prove the theoretical limit of GMM and the consistency result, assuming that the data follow an elliptical distribution, which is a very general family of distributions and includes the multivariate t-distribution as a special case. The consistency result holds as long as the data have bounded first moment (an assumption which essentially holds for datasets commonly encountered in practice). Furthermore, we establish the asymptotic normality of GMM. Compared to the "cosine" similarity which is routinely adopted in current practice in statistics and machine learning, the consistency of GMM requires much weaker conditions. Interestingly, when the data follow the t-distribution with nu degrees of freedom, GMM typically provides a better measure of similarity than "cosine" roughly when nu<8 (which is already very close to normal). These theoretical results will help explain the recent success of GMM in learning tasks.