REVIEW 3 cited by
A theory of continuous generative flow networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 3 Pith papers
-
A Distributional Framework for Generative Modeling of Molecular Crystals
MXtalGFlow combines a canonical crystal parameterization with energy-based GFlowNet training to sample thermodynamic distributions of molecular crystals, recovering known polymorphs and predicting new competitive pack...
-
No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers
Simulation-free training of neural samplers fails without Langevin preconditioning, and parallel tempering followed by fitting a diffusion model is a stronger baseline than most neural samplers.
-
Effective Reward Specification in Deep Reinforcement Learning
A thesis presenting four methods (ASAF, TeamReg, CoachReg, constrained RL, goal-conditioned GFlowNets) that improve reward specification for deep RL through demonstrations, policy regularization, behavior constraints,...
Discussion (0). Continue with ORCID to comment.