Saved in:
Bibliographic Details
Main Authors: González, Fabio A., Ramos-Pollán, Raúl, Gallego-Mejia, Joseph A.
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.18204
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929330724012032
author González, Fabio A.
Ramos-Pollán, Raúl
Gallego-Mejia, Joseph A.
author_facet González, Fabio A.
Ramos-Pollán, Raúl
Gallego-Mejia, Joseph A.
contents This paper introduces a novel approach to probabilistic deep learning, kernel density matrices, which provide a simpler yet effective mechanism for representing joint probability distributions of both continuous and discrete random variables. In quantum mechanics, a density matrix is the most general way to describe the state of a quantum system. This work extends the concept of density matrices by allowing them to be defined in a reproducing kernel Hilbert space. This abstraction allows the construction of differentiable models for density estimation, inference, and sampling, and enables their integration into end-to-end deep neural models. In doing so, we provide a versatile representation of marginal and joint probability distributions that allows us to develop a differentiable, compositional, and reversible inference procedure that covers a wide range of machine learning tasks, including density estimation, discriminative learning, and generative modeling. The broad applicability of the framework is illustrated by two examples: an image classification model that can be naturally transformed into a conditional generative model, and a model for learning with label proportions that demonstrates the framework's ability to deal with uncertainty in the training samples. The framework is implemented as a library and is available at: https://github.com/fagonzalezo/kdm.
format Preprint
id arxiv_https___arxiv_org_abs_2305_18204
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Kernel Density Matrices for Probabilistic Deep Learning
González, Fabio A.
Ramos-Pollán, Raúl
Gallego-Mejia, Joseph A.
Machine Learning
Quantum Physics
I.2.6
This paper introduces a novel approach to probabilistic deep learning, kernel density matrices, which provide a simpler yet effective mechanism for representing joint probability distributions of both continuous and discrete random variables. In quantum mechanics, a density matrix is the most general way to describe the state of a quantum system. This work extends the concept of density matrices by allowing them to be defined in a reproducing kernel Hilbert space. This abstraction allows the construction of differentiable models for density estimation, inference, and sampling, and enables their integration into end-to-end deep neural models. In doing so, we provide a versatile representation of marginal and joint probability distributions that allows us to develop a differentiable, compositional, and reversible inference procedure that covers a wide range of machine learning tasks, including density estimation, discriminative learning, and generative modeling. The broad applicability of the framework is illustrated by two examples: an image classification model that can be naturally transformed into a conditional generative model, and a model for learning with label proportions that demonstrates the framework's ability to deal with uncertainty in the training samples. The framework is implemented as a library and is available at: https://github.com/fagonzalezo/kdm.
title Kernel Density Matrices for Probabilistic Deep Learning
topic Machine Learning
Quantum Physics
I.2.6
url https://arxiv.org/abs/2305.18204