English
Related papers

Related papers: Algebraic Identifiability of Gaussian Mixtures

200 papers

We show, by an explicit construction, that a mixture of univariate Gaussian densities with variance $1$ and means in $[-A,A]$ can have $\Omega(A^2)$ modes. This disproves a recent conjecture of Dytso, Yagli, Poor and Shamai \cite{DYPS20}…

Statistics Theory · Mathematics 2020-10-23 Navin Kashyap , Manjunath Krishnapur

The starting point of this work is a theorem due to Maxwell characterizing the distribution of a Gaussian vector with at least two coordinates. We define the Gaussian orthogonal, unitary and symplectic tensor ensembles for notions of real…

Mathematical Physics · Physics 2026-04-02 Rémi Bonnin

This work provides a computationally efficient and statistically consistent moment-based estimator for mixtures of spherical Gaussians. Under the condition that component means are in general position, a simple spectral decomposition…

Machine Learning · Computer Science 2012-10-30 Daniel Hsu , Sham M. Kakade

We prove multi-dimensional central limit theorems for the spectral moments (of arbitrary degrees) associated with random matrices with real-valued i.i.d. entries, satisfying some appropriate moment conditions. Our techniques rely on a…

Probability · Mathematics 2009-09-30 Ivan Nourdin , Giovanni Peccati

The Hurwitz form of a projective variety characterizes linear spaces of complementary dimension which meet the variety non-transversally. We extend this notion to varieties in a product of projective spaces. This parallels the multigraded…

Algebraic Geometry · Mathematics 2026-02-24 Elizabeth Pratt , Luca Sodomaco , Bernd Sturmfels

The long-standing Alekseevskii conjecture states that a connected homogeneous Einstein space G/K of negative scalar curvature must be diffeomorphic to R^n. This was known to be true only in dimensions up to 5, and in dimension 6 for…

Differential Geometry · Mathematics 2016-02-22 Romina M. Arroyo , Ramiro A. Lafuente

We prove a conjecture due to Sturmfels and Uhler concerning the degree of the projective variety associated to the Gaussian graphical model of the cycle. We involve new methods based on the intersection theory in the space of complete…

Algebraic Geometry · Mathematics 2021-11-05 Rodica Andreea Dinu , Mateusz Michałek , Martin Vodička

The predictions of the Mirror Symmetry are extended in dimensions n>3 and are proven for projective complete intersections Calabi-Yau varieties. Precisely, we prove that the total collection of rational Gromov-Witten invariants of such…

Algebraic Geometry · Mathematics 2019-06-04 Sergey Barannikov

It is conjectured that the dual variety of every smooth nonlinear subvariety of dimension $> \frac{2N}{3}$ in projective $N$-space is a hypersurface, an expectation known as the duality defect conjecture. This would follow from the truth of…

Algebraic Geometry · Mathematics 2020-07-01 Grayson Jorgenson

We consider estimating the parameters of a Gaussian mixture density with a given number of components best representing a given set of weighted samples. We adopt a density interpretation of the samples by viewing them as a discrete Dirac…

Machine Learning · Statistics 2025-04-03 Daniel Frisch , Uwe D. Hanebeck

We present a general method which can be used for geometrical and physical interpretation of an arbitrary spacetime in four or any higher number of dimensions. It is based on the systematic analysis of relative motion of free test…

General Relativity and Quantum Cosmology · Physics 2015-06-03 Jiri Podolsky , Robert Svarc

In this paper, we establish the following version at infinity of Whitney's theorem [6, 7]: Geometric and algebraic tangent cones at infinity of complex algebraic varieties coincide. The proof of this fact is based on a geometric…

Algebraic Geometry · Mathematics 2016-03-22 Công-Trình Lê , Tien-Son Pham

A well known theorem by Alexander-Hirschowitz states that all the higher secant varieties of $V_{n,d}$ (the $d$-uple embedding of $\mathbb{P}^n$) have the expected dimension, with few known exceptions. We study here the same problem for…

Algebraic Geometry · Mathematics 2011-05-19 A. Bernardi , M. V. Catalisano , A. Gimigliano , M. Idà

We study the efficient learnability of high-dimensional Gaussian mixtures in the outlier-robust setting, where a small constant fraction of the data is adversarially corrupted. We resolve the polynomial learnability of this problem when the…

Data Structures and Algorithms · Computer Science 2020-05-14 Ilias Diakonikolas , Samuel B. Hopkins , Daniel Kane , Sushrut Karmalkar

In this paper, we establish some modified defect relations for the Gauss map $g$ of a complete minimal surface $S\subset\mathbb R^m$ into a $k$-dimension projective subvariety $V\subset\mathbb P^n(\mathbb C)\ (n=m-1)$ with hypersurfaces…

Differential Geometry · Mathematics 2024-09-24 Si Duc Quang

The Method of Moments [Pea94] is one of the most widely used methods in statistics for parameter estimation, by means of solving the system of equations that match the population and estimated moments. However, in practice and especially…

Statistics Theory · Mathematics 2019-04-16 Yihong Wu , Pengkun Yang

Given a complex vector space $V$ of finite dimension, its Grassmannian variety parametrizes all subspaces of $V$ of a given dimension. Similarly, if a finite group $G$ acts on $V$, its invariant Grassmannian parametrizes all the…

Algebraic Geometry · Mathematics 2024-05-01 Stevell Muller

For any quantum system invariant under gauging a higher-form global symmetry, we construct a non-invertible topological defect by gauging in only half of spacetime. This generalizes the Kramers-Wannier duality line in 1+1 dimensions to…

High Energy Physics - Theory · Physics 2022-07-13 Yichul Choi , Clay Cordova , Po-Shen Hsin , Ho Tat Lam , Shu-Heng Shao

In this paper we describe all possible reduced complete intersection sets of points on Veronese surfaces. We formulate a conjecture for the general case of complete intersection subvarieties of any dimension and we prove it in the case of…

Algebraic Geometry · Mathematics 2022-07-08 Stefano Canino , Enrico Carlini

This paper deals with Bayesian inference of a mixture of Gaussian distributions. A novel formulation of the mixture model is introduced, which includes the prior constraint that each Gaussian component is always assigned a minimal number of…

Methodology · Statistics 2014-05-21 Colin J. Stoneking