In this paper, we introduce Woodbury transformations, which achieve efficient invertibility via the Woodbury matrix identity and efficient determinant ...
scholar.google.com › citations
In our experiments on multiple image datasets, we find that Woodbury transformations allow learning of higher-likelihood models than other flow architectures ...
Feb 27, 2020 · In this paper, we introduce Woodbury transformations, which achieve efficient invertibility via the Woodbury matrix identity and efficient ...
In our experiments on multiple image datasets, we find that Woodbury transformations allow learning of higher-likelihood models than other flow architectures ...
The paper proposes to parameterize a linear transformation as a low-rank update to an identity matrix, and then use the Woodbury matrix identity to ...
Summary and Contributions: The paper introduces an efficient transformation. This model constructs a dense fully connected layer with a low rank plus identity ...
In our experiments on multiple image datasets, we find that Woodbury transformations allow learning of higher-likelihood models than other flow architectures ...
Woodbury transformations are introduced, which achieve efficient invertibility via the Woodbury matrix identity and efficient determinant calculation via ...
This code is a Python implementation of the Woodbury Transformations introduced in the paper. "Woodbury Transformations for Deep Generative Flows".
Dec 6, 2020 · In this paper, we introduce Woodbury transformations, which achieve efficient invertibility via the Woodbury matrix identity and efficient ...