English
Related papers

Related papers: On Learning Parallel Pancakes with Mostly Uniform …

200 papers

High-dimensional PDEs have been a longstanding computational challenge. We propose to solve high-dimensional PDEs by approximating the solution with a deep neural network which is trained to satisfy the differential operator, initial…

Mathematical Finance · Quantitative Finance 2018-10-17 Justin Sirignano , Konstantinos Spiliopoulos

In this work, we propose variations of a Gaussian mixture model (GMM) based channel estimator that was recently proven to be asymptotically optimal in the minimum mean square error (MMSE) sense. We account for the need of low computational…

Information Theory · Computer Science 2023-06-06 Benedikt Fesl , Michael Joham , Sha Hu , Michael Koller , Nurettin Turan , Wolfgang Utschick

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 consider the problem of clustering mixtures of mean-separated Gaussians in high dimensions. We are given samples from a mixture of $k$ identity covariance Gaussians, so that the minimum pairwise distance between any two pairs of means is…

Data Structures and Algorithms · Computer Science 2021-12-02 Jerry Li , Allen Liu

We study the complexity of training neural network models with one hidden nonlinear activation layer and an output weighted sum layer. We analyze Gradient Descent applied to learning a bounded target function on $n$ real-valued inputs. We…

Machine Learning · Computer Science 2019-05-28 Santosh Vempala , John Wilmes

The k-means algorithm is a well-known method for partitioning n points that lie in the d-dimensional space into k clusters. Its main features are simplicity and speed in practice. Theoretically, however, the best known upper bound on its…

Computational Geometry · Computer Science 2008-12-03 Andrea Vattani

Deep learning is a hierarchical inference method formed by subsequent multiple layers of learning able to more efficiently describe complex relationships. In this work, Deep Gaussian Mixture Models are introduced and discussed. A Deep…

Machine Learning · Statistics 2017-11-21 Cinzia Viroli , Geoffrey J. McLachlan

Solving polynomial systems arising from applications is frequently made easier by the structure of the systems. Weighted homogeneity (or quasi-homogeneity) is one example of such a structure: given a system of weights…

Symbolic Computation · Computer Science 2015-12-22 Jean-Charles Faugère , Mohab Safey El Din , Thibaut Verron

We present a fairly general framework for reducing $(\varepsilon, \delta)$ differentially private (DP) statistical estimation to its non-private counterpart. As the main application of this framework, we give a polynomial time and…

Machine Learning · Statistics 2022-06-23 Hassan Ashtiani , Christopher Liaw

We investigate the convergence properties of the EM algorithm when applied to overspecified Gaussian mixture models -- that is, when the number of components in the fitted model exceeds that of the true underlying distribution. Focusing on…

Machine Learning · Statistics 2025-06-16 Zhenisbek Assylbekov , Alan Legg , Artur Pak

In order to cluster or partition data, we often use Expectation-and-Maximization (EM) or Variational approximation with a Gaussian Mixture Model (GMM), which is a parametric probability density function represented as a weighted sum of…

Machine Learning · Computer Science 2013-07-04 Ji Won Yoon

We quantify the parameter stability of a spherical Gaussian Mixture Model (sGMM) under small perturbations in distribution space. Namely, we derive the first explicit bound to show that for a mixture of spherical Gaussian $P$ (sGMM) in a…

Machine Learning · Statistics 2023-02-02 Hanyu Zhang , Marina Meila

We consider the problem of learning mixtures of Gaussians under the constraint of approximate differential privacy. We prove that $\widetilde{O}(k^2 d \log^{3/2}(1/\delta) / \alpha^2 \varepsilon)$ samples are sufficient to learn a mixture…

Machine Learning · Computer Science 2021-06-07 Ishaq Aden-Ali , Hassan Ashtiani , Christopher Liaw

Gaussian mixtures are a powerful and widely used tool to model non-Gaussian estimation problems. They are able to describe measurement errors that follow arbitrary distributions and can represent ambiguity in assignment tasks like point set…

Robotics · Computer Science 2021-04-02 Tim Pfeifer , Sven Lange , Peter Protzel

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

The classical $k$-means algorithm for partitioning $n$ points in $\mathbb{R}^d$ into $k$ clusters is one of the most popular and widely spread clustering methods. The need to respect prescribed lower bounds on the cluster sizes has been…

Optimization and Control · Mathematics 2016-08-04 Steffen Borgwardt , Andreas Brieden , Peter Gritzmann

Gaussian graphical models (GGMs) are widely used for statistical modeling, because of ease of inference and the ubiquitous use of the normal distribution in practical approximations. However, they are also known for their limited modeling…

Machine Learning · Statistics 2016-11-22 Qinliang Su , Xuejun Liao , Chunyuan Li , Zhe Gan , Lawrence Carin

This paper analyzes the convergence and generalization of training a one-hidden-layer neural network when the input features follow the Gaussian mixture model consisting of a finite number of Gaussian distributions. Assuming the labels are…

Machine Learning · Computer Science 2023-01-30 Hongkang Li , Shuai Zhang , Meng Wang

Learning a Gaussian Mixture Model (GMM) is hard when the number of parameters is too large given the amount of available data. As a remedy, we propose restricting the GMM to a Gaussian Markov Random Field Mixture Model (GMRF-MM), as well as…

Machine Learning · Computer Science 2022-01-25 Shahaf E. Finder , Eran Treister , Oren Freifeld

The Expectation-Maximization (EM) algorithm is a fundamental tool in unsupervised machine learning. It is often used as an efficient way to solve Maximum Likelihood (ML) estimation problems, especially for models with latent variables. It…

Quantum Physics · Physics 2020-07-08 Iordanis Kerenidis , Alessandro Luongo , Anupam Prakash
‹ Prev 1 3 4 5 6 7 10 Next ›