Bounds on the Number of Modes of a Gaussian Mixture Density
Hien Duy Nguyen

TL;DR
This paper establishes explicit upper and lower bounds on the number of modes and critical points of Gaussian mixture densities in multiple dimensions, advancing understanding of their geometric complexity.
Contribution
It introduces new algebraic bounds and Morse-theoretic methods for quantifying the critical points and modes of Gaussian mixtures, including dimension-free and homoscedastic cases.
Findings
Derived explicit upper bounds for critical points and modes of Gaussian mixtures.
Provided lower bounds and constructions for the number of critical points.
Improved bounds for special cases like homoscedastic mixtures.
Abstract
We derive explicit upper bounds for the number of nondegenerate critical points of a -component Gaussian mixture density in , and the number of modes when the modal set is finite, together with lower bounds. By normalizing the critical-point equations by a reference component, for we get the direct Pfaffian bound \[ U_{\mathrm{het}}(d,k)=2^{\,d+\binom{k-1}{2}}\left(d+2\min(d,k-1)+1\right)^{k-1}. \] For the same parameter range, an exact elimination augmented by an algebraic reciprocal variable gives the alternative bound \[ U_{\mathrm{aug}}(d,k)= 2^{\binom{k-1}{2}}(d+1)\left((2k-1)d+2k-1\right)^{k-1}. \] Thus, for , the best critical-point bound is their minimum. A Morse-theoretic argument improves the corresponding finite-mode upper bound to \[ \left\lfloor \frac{\min\{U_{\mathrm{het}}(d,k),U_{\mathrm{aug}}(d,k)\}+1}{2}\right\rfloor. \] In the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
