A theory of continuous generative flow networks
This work addresses a key bottleneck for researchers and practitioners in probabilistic inference by enabling GFlowNets to handle continuous spaces, though it is incremental as it builds on existing discrete GFlowNets.
The paper tackles the limitation of Generative Flow Networks (GFlowNets) being restricted to discrete spaces by developing a theory that extends them to continuous or hybrid state spaces, and demonstrates strong empirical results compared to baselines on several tasks.
Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target distributions over compositional objects. A key limitation of GFlowNets until this time has been that they are restricted to discrete spaces. We present a theory for generalized GFlowNets, which encompasses both existing discrete GFlowNets and ones with continuous or hybrid state spaces, and perform experiments with two goals in mind. First, we illustrate critical points of the theory and the importance of various assumptions. Second, we empirically demonstrate how observations about discrete GFlowNets transfer to the continuous case and show strong results compared to non-GFlowNet baselines on several previously studied tasks. This work greatly widens the perspectives for the application of GFlowNets in probabilistic inference and various modeling settings.