paper-with-me

Papers

Efficient Deep Learning of GMMs

2019-02-15 · Shirin Jalali, Carl Nuzman, Iraj Saniee

We show that a collection of Gaussian mixture models (GMMs) in $R^{n}$ can be optimally classified using $O(n)$ neurons in a neural network with two hidden layers (deep neural network), whereas in contrast, a neural network with a single hidden layer (shallow neural network) would require at least $O(\exp(n))$ neurons or possibly exponentially large coefficients. Given the universality of the Gaussian distribution in the feature spaces of data, e.g., in speech, image and text, our result sheds light on the observed efficiency of deep neural networks in practical classification problems.

📄 PDF Abstract BibTeX arXiv:1902.05707

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningGeneral Classification

Similar Papers 제목 키워드 기반

Image Modeling with Deep Convolutional Gaussian Mixture Models

2021-04-19 · Alexander Gepperth, Benedikt Pfülb

In this conceptual work, we present Deep Convolutional Gaussian Mixture Models (DCGMMs): a new formulation of deep hierarchical Gaussian Mixture Models (GMMs) that is particularly suitable for describing and generating i…

ClusteringOutlier Detection

GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models

2022-10-05 · Chen Liang, Wenguan Wang, Jiaxu Miao, Yi Yang

Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier of p(class|pixel feature). Though straightforward, this de facto paradigm neglects the underlying data distribution p(pixel fea…

Out-of-Distribution DetectionSegmentationSemantic Segmentation

Scaling Limits of the Wasserstein information matrix on Gaussian Mixture Models

2023-09-22 · Wuchen Li, Jiaxi Zhao

We consider the Wasserstein metric on the Gaussian mixture models (GMMs), which is defined as the pullback of the full Wasserstein metric on the space of smooth probability distributions with finite second moment. It der…

Distance Measure Based on an Embedding of the Manifold of K-Component Gaussian Mixture Models into the Manifold of Symmetric Positive Definite Matrices

2025-01-13 · Amit Vishwakarma, KS Subrahamanian Moosath

In this paper, a distance between the Gaussian Mixture Models(GMMs) is obtained based on an embedding of the K-component Gaussian Mixture Model into the manifold of the symmetric positive definite matrices. Proof of embe…

Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters

2025-01-21 · Sebastian Salwig, Till Kahlke, Florian Hirschberger, Dennis Forster 외

Gaussian Mixture Models (GMMs) range among the most frequently used machine learning models. However, training large, general GMMs becomes computationally prohibitive for datasets with many data points $N$ of high-dimens…

CPU