This article is within the scope of WikiProject Statistics, a collaborative effort to improve the coverage of statistics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.StatisticsWikipedia:WikiProject StatisticsTemplate:WikiProject StatisticsStatistics
This article is within the scope of WikiProject Computer science, a collaborative effort to improve the coverage of Computer science related articles on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.Computer scienceWikipedia:WikiProject Computer scienceTemplate:WikiProject Computer scienceComputer science
Latest comment: 11 months ago1 comment1 person in discussion
I added references to Bell & Sejnowski (1995) and Roth & Baram (1996). These papers first applied log-Jacobian differentiation to estimate probability densities (pdfs) and cumulative distributions (cdfs), respectively. In effect, they are the single-layer cases of what is now called flow-based generative modeling.
These contributions are rarely acknowledged in the current "generative flows" literature, which tends to start with NICE (2014). The situation is somewhat analogous to perceptrons vs. multilayer perceptrons: perceptrons are not often cited, but everyone knows Rosenblatt’s work existed. The intent of adding these references is to provide historical accuracy and context, not to diminish later developments. 2A00:23C7:C32F:2E01:4842:4626:DC5:94C3 (talk) 00:50, 22 August 2025 (UTC)Reply
