Information-Geometric Forward Policy Training in GFlowNets

• URL: http://arxiv.org/abs/2608.03967v1
• Date: Tue, 04 Aug 2026 17:34:14 GMT
• Title: Information-Geometric Forward Policy Training in GFlowNets
• Abstract summary: We formulate forward-policy training in GFlowNets through the information geometry of the induced trajectory sampler.<n>Treating the forward policy as an induced trajectory sampler, we show that its intrinsic first-order geometry is given by the Fisher-Rao metric of the trajectory family.<n>We derive an exact decomposition of the trajectory Fisher into per-step conditional second moments.
• Score: 1.9480051045857554
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative Flow Networks (GFlowNets) have emerged as a flexible framework for amortised inference over discrete and mixed discrete-continuous objects, requiring only an unnormalised target density specified through a reward. In this work, we formulate forward-policy training in GFlowNets through the information geometry of the induced trajectory sampler. Treating the forward policy as an induced trajectory sampler, we show that its intrinsic first-order geometry is given by the Fisher-Rao metric of the trajectory family, and that the associated natural gradient provides the canonical local update whenever the corresponding Fisher information is computable or accurately approximable. We derive an exact decomposition of the trajectory Fisher into per-step conditional second moments, which clarifies when temporal score interactions vanish and when dense couplings remain under shared parameterisation. This leads to three computational regimes: settings with tractable exact Fisher information, settings where Monte Carlo estimators of the expected Fisher are sufficient, and structure-exploitable settings in which target locality or factorisation yields accurate approximations of the Fisher expectation. In the latter case, graphical-model tools such as exact marginalisation, separator methods, and belief propagation provide principled surrogates for natural-gradient updates. The resulting framework turns target structure into optimisation geometry and yields a tractable route to structure-aware forward-policy training in GFlowNets. We illustrate the framework empirically through examples comparing convergence and exploration behaviour under Riemannian and Euclidean optimisation.

Related papers

• CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification [52.452902154360565]
  CuBAS is an information-geometric framework for adaptive data selection in supervised classification.<n>A labeled dataset can be viewed as a statistical manifold, on which local curvature, estimated via the ratio of second to first-order observed Fisher information, faithfully encodes the geometric complexity of the data distribution.
  arXiv  Detail & Related papers  (2026-07-03T09:36:02Z)
• Path Integral Approach to Quantum Fisher Information [1.0005747083373795]
  We show that the quantum Fisher information can be expressed as a connected symmetrized covariance of a time-integrated action deformation.<n>This reformulation avoids explicit state reconstruction by rewriting the quantum Fisher information in terms of real-time correlators.
  arXiv  Detail & Related papers  (2026-04-14T14:06:20Z)
• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• FISMO: Fisher-Structured Momentum-Orthogonalized Optimizer [30.184978506988767]
  We introduce FISMO, which incorporates anisotropic neuralotropic geometry information through Fisher information geometry.<n> FISMO achieves superior efficiency and final performance compared to established baselines.
  arXiv  Detail & Related papers  (2026-01-29T14:05:04Z)
• Bridging Training and Merging Through Momentum-Aware Optimization [8.035521056416242]
  Training large neural networks and task-specific computation models require parameter importance estimation.<n>Current compute curvature information during training, discard it, then recompute similar information for merging.<n>We introduce a unified framework that factorized momentum and curvature statistics during training, then recompute similar information for merging.
  arXiv  Detail & Related papers  (2025-12-18T22:37:33Z)
• Fisher Flow Matching for Generative Modeling over Discrete Data [12.69975914345141]
  We introduce Fisher-Flow, a novel flow-matching model for discrete data. Fisher-Flow takes a manifestly geometric perspective by considering categorical distributions over discrete data. We prove that the gradient flow induced by Fisher-Flow is optimal in reducing the forward KL divergence.
  arXiv  Detail & Related papers  (2024-05-23T15:02:11Z)
• Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network [59.79008107609297]
  We propose in this paper to approximate the joint posterior over the structure of a Bayesian Network. We use a single GFlowNet whose sampling policy follows a two-phase process. Since the parameters are included in the posterior distribution, this leaves more flexibility for the local probability models.
  arXiv  Detail & Related papers  (2023-05-30T19:16:44Z)
• Distributional GFlowNets with Quantile Flows [73.73721901056662]
  Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a policy for generating complex structure through a series of decision-making steps. In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training. Our proposed textitquantile matching GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty.
  arXiv  Detail & Related papers  (2023-02-11T22:06:17Z)
• Learning GFlowNets from partial episodes for improved convergence and stability [56.99229746004125]
  Generative flow networks (GFlowNets) are algorithms for training a sequential sampler of discrete objects under an unnormalized target density. Existing training objectives for GFlowNets are either local to states or transitions, or propagate a reward signal over an entire sampling trajectory. Inspired by the TD($lambda$) algorithm in reinforcement learning, we introduce subtrajectory balance or SubTB($lambda$), a GFlowNet training objective that can learn from partial action subsequences of varying lengths.
  arXiv  Detail & Related papers  (2022-09-26T15:44:24Z)
• Bayesian Structure Learning with Generative Flow Networks [85.84396514570373]
  In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) from data. Recently, a class of probabilistic models, called Generative Flow Networks (GFlowNets), have been introduced as a general framework for generative modeling. We show that our approach, called DAG-GFlowNet, provides an accurate approximation of the posterior over DAGs.
  arXiv  Detail & Related papers  (2022-02-28T15:53:10Z)
• The Bayesian Method of Tensor Networks [1.7894377200944511]
  We study the Bayesian framework of the Network from two perspective. We study the Bayesian properties of the Network by visualizing the parameters of the model and the decision boundaries in the two dimensional synthetic data set.
  arXiv  Detail & Related papers  (2021-01-01T14:59:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.