Timezone: »

Training Normalizing Flows from Dependent Data
Matthias Kirchler · Christoph Lippert · Marius Kloft

Tue Jul 25 05:00 PM -- 06:30 PM (PDT) @ Exhibit Hall 1 #627

Normalizing flows are powerful non-parametric statistical models that function as a hybrid between density estimators and generative models. Current learning algorithms for normalizing flows assume that data points are sampled independently, an assumption that is frequently violated in practice, which may lead to erroneous density estimation and data generation. We propose a likelihood objective of normalizing flows incorporating dependencies between the data points, for which we derive a flexible and efficient learning algorithm suitable for different dependency structures. We show that respecting dependencies between observations can improve empirical results on both synthetic and real-world data, and leads to higher statistical power in a downstream application to genome-wide association studies.

Author Information

Matthias Kirchler (Hasso Plattner Institute)
Christoph Lippert (Hasso Plattner Insitute for Digital Engineering, Universität Potsdam)
Marius Kloft (TU Kaiserslautern)

More from the Same Authors