By Patrik Róbert Gerber and others

We propose a new density estimation algorithm. Given *n* i.i.d. samples from a distribution belonging to a class of densities on *\mathbb{R}^d*, our estimator outputs any density in the class whose ''perceptron discrepancy'' with the empirical distribution is at most *O(\sqrt{d/n})*. The perceptron discrepancy between two distributions is defined as... Show more

February 20, 2024

Loading full text...

Similar articles

Loading recommendations...

x1

Density estimation using the perceptron

Click on play to start listening