Fourier Basis Density Model

arXiv:2402.15345v1 Announce Type: new
Abstract: We introduce a lightweight, flexible and end-to-end trainable probability density model parameterized by a constrained Fourier basis. We assess its performance at approximating a range of multi-modal 1D densities, which are generally difficult to fit. In comparison to the deep factorized model introduced in [1], our model achieves a lower cross entropy at a similar computational budget. In addition, we also evaluate our method on a toy compression task, demonstrating its utility in learned compression.

abstract arxiv comparison cs.lg fourier modal multi-modal performance probability stat.ml type