Deep Conditional Measure Quantization
Machine Learning
2024-02-12 v2 Artificial Intelligence
Machine Learning
Probability
Abstract
Quantization of a probability measure means representing it with a finite set of Dirac masses that approximates the input distribution well enough (in some metric space of probability measures). Various methods exists to do so, but the situation of quantizing a conditional law has been less explored. We propose a method, called DCMQ, involving a Huber-energy kernel-based approach coupled with a deep neural network architecture. The method is tested on several examples and obtains promising results.
Cite
@article{arxiv.2301.06907,
title = {Deep Conditional Measure Quantization},
author = {Gabriel Turinici},
journal= {arXiv preprint arXiv:2301.06907},
year = {2024}
}