Exchangeable Generative Models with Flow Scans
This addresses the problem of modeling exchangeable data for researchers in machine learning, representing a novel method rather than an incremental improvement.
The authors tackled generative density estimation for exchangeable, non-i.i.d. data by developing FlowScan, which combines invertible flow transformations with a sorted scan to model data while preserving exchangeability, achieving new state-of-the-art performance on point cloud and image set modeling.
In this work, we develop a new approach to generative density estimation for exchangeable, non-i.i.d. data. The proposed framework, FlowScan, combines invertible flow transformations with a sorted scan to flexibly model the data while preserving exchangeability. Unlike most existing methods, FlowScan exploits the intradependencies within sets to learn both global and local structure. FlowScan represents the first approach that is able to apply sequential methods to exchangeable density estimation without resorting to averaging over all possible permutations. We achieve new state-of-the-art performance on point cloud and image set modeling.