gflownets - Robuta Search

https://openreview.net/forum?id=ZBUthI6wK9h Robust Scheduling with GFlowNets | OpenReview We use GFlowNets for robust scheduling. robust scheduling gflownets openreview https://openreview.net/forum?id=ghNQhtCHD2 Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design | OpenReview In recent years, in-silico molecular design has received much attention from the machine learning community. When designing a new compound for pharmaceutical... multi objective molecular design goal conditioned gflownets https://openreview.net/forum?id=PJNhZoCjLh Generalization and Distributed Learning of GFlowNets | OpenReview Conventional wisdom attributes the success of Generative Flow Networks (GFlowNets) to their ability to exploit the compositional structure of the sample space... distributed learning generalization gflownets openreview https://openreview.net/forum?id=9GsgCUJtic When do GFlowNets learn the right distribution? | OpenReview Generative Flow Networks (GFlowNets) are an emerging class of sampling methods for distributions over discrete and compositional objects, e.g., graphs. In... when do the right gflownets learn distribution https://openreview.net/forum?id=vFSsRYGpjW Distributional GFlowNets with Quantile Flows | OpenReview Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a stochastic policy for generating complex combinatorial... distributional gflownets quantile flows openreview https://openreview.net/forum?id=uoG1fLIK2s Sample-efficient Multi-objective Molecular Optimization with GFlowNets | OpenReview Many crucial scientific problems involve designing novel molecules with desired properties, which can be formulated as a black-box optimization problem over... multi objective sample efficient molecular optimization https://openreview.net/forum?id=sTjW3JHs2V Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets | OpenReview Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning... let flows tell solving