paper-with-me

홈 › Papers

Global-Order GFlowNets

2025-04-03 · Lluís Pastor-Pérez, Javier Alonso-Garcia, Lukas Mauch

Order-Preserving (OP) GFlowNets have demonstrated remarkable success in tackling complex multi-objective (MOO) black-box optimization problems using stochastic optimization techniques. Specifically, they can be trained online to efficiently sample diverse candidates near the Pareto front. A key advantage of OP GFlowNets is their ability to impose a local order on training samples based on Pareto dominance, eliminating the need for scalarization - a common requirement in other approaches like Preference-Conditional GFlowNets. However, we identify an important limitation of OP GFlowNets: imposing a local order on training samples can lead to conflicting optimization objectives. To address this issue, we introduce Global-Order GFlowNets, which transform the local order into a global one, thereby resolving these conflicts. Our experimental evaluations on various benchmarks demonstrate the efficacy and promise of our proposed method.

📄 PDF Abstract BibTeX arXiv:2504.02968

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

Order-Preserving GFlowNets

2023-09-30 · Yihang Chen, Lukas Mauch

Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates with probabilities proportional to a given reward. However, GFlowNets can only be used with a predefined scalar …

Neural Architecture Search

GFlowNets for AI-Driven Scientific Discovery

2023-02-01 · Moksh Jain, Tristan Deleu, Jason Hartford, Cheng-Hao Liu 외

Tackling the most pressing problems for humanity, such as the climate crisis and the threat of global pandemics, requires accelerating the pace of scientific discovery. While science has traditionally relied on trial and…

Efficient ExplorationExperimental Designscientific discovery

Embarrassingly Parallel GFlowNets

2024-06-05 · Tiago da Silva, Luiz Max Carvalho, Amauri Souza, Samuel Kaski 외

GFlowNets are a promising alternative to MCMC sampling for discrete compositional random variables. Training GFlowNets requires repeated evaluations of the unnormalized target distribution or reward function. However, fo…

Trajectory balance: Improved credit assignment in GFlowNets

2022-01-31 · Nikolay Malkin, Moksh Jain, Emmanuel Bengio, Chen Sun 외

Generative flow networks (GFlowNets) are a method for learning a stochastic policy for generating compositional objects, such as graphs or strings, from a given unnormalized density by sequences of actions, where many po…

Diversity

Stable GFlowNets with Probabilistic Guarantees

2026-05-03 · Zengxiang Lei, Ananth Shreekumar, Jonathan Rosenthal, Ruoyu Song 외 arxiv

Generative Flow Networks (GFlowNets) learn to sample states proportional to an unnormalized reward. Despite their theoretical promise, practical training is often unstable, exhibiting severe loss spikes and mode collapse…