Learning a Mixture of GFlowNets

cs.LG, cs.AI, stat.ML

Submitted: 2026-10-06

Updated: 2026-10-06

Code: https://github.com/oogle/flax

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Action abstractions for amortized sampling
• Variational Inference with Continuously-Indexed Normalizing Flows
• AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration
• Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
• Avoid What You Know: Divergent Trajectory Balance for GFlowNets
• Generative Flow Networks: a Markov Chain Perspective
• Discrete Probabilistic Inference as Control in Multi-path Environments
• Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization
• Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks
• Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Models
• Local Search GFlowNets
• Learning to Scale Logits for Temperature-Conditional GFlowNets
• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• Curriculum-Augmented GFlowNets For mRNA Sequence Generation
• GFN-SR: Symbolic Regression with Generative Flow Networks
• Generative Marginalization Models
• Revisiting Non-Acyclic GFlowNets in Discrete Environments
• Better Training of GFlowNets with Local Credit and Incomplete Trajectories
• GFlowNet Pretraining with Inexpensive Rewards

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks