DEMANDE: Density Matrix Neural Density Estimation

Density estimation is a fundamental task in statistics and machine learning that aims to estimate, from set of samples, the probability density function distribution generated them. There are different methods for addressing this problem but recently deep-neural have emerged as powerful alternative. This paper presents novel method neural based on matrices adaptive Fourier features. commonly used quantum mechanics represent state physical system. In work, they estimate densities using an operation called measurement. The proposed can be trained without optimization averaging over samples training dataset. It also integrated with deep architectures gradient descent. performance was evaluated range synthetic real datasets compared fast kernel state-of-the-art methods. results demonstrate achieves competitive while being faster more efficient than existing