General Proximal Flow Networks

• URL: http://arxiv.org/abs/2603.00751v1
• Date: Sat, 28 Feb 2026 17:52:44 GMT
• Title: General Proximal Flow Networks
• Abstract summary: This paper introduces General Proximal Flow Networks (GPFNs)<n>GPFNs replace the fixed choice with an arbitrary divergence or distance function, such as the Wasserstein distance.<n> Empirical evaluations confirm that adapting the divergence to the underlying data geometry yields measurable improvements in generation quality.
• Score: 41.99844472131922
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces General Proximal Flow Networks (GPFNs), a generalization of Bayesian Flow Networks that broadens the class of admissible belief-update operators. In Bayesian Flow Networks, each update step is a Bayesian posterior update, which is equivalent to a proximal step with respect to the Kullback-Leibler divergence. GPFNs replace this fixed choice with an arbitrary divergence or distance function, such as the Wasserstein distance, yielding a unified proximal-operator framework for iterative generative modeling. The corresponding training and sampling procedures are derived, establishing a formal link to proximal optimization and recovering the standard BFN update as a special case. Empirical evaluations confirm that adapting the divergence to the underlying data geometry yields measurable improvements in generation quality, highlighting the practical benefits of this broader framework.

Related papers

• Information-Geometric Forward Policy Training in GFlowNets [1.9480051045857554]
  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.
  arXiv  Detail & Related papers  (2026-08-04T17:34:14Z)
• RBE-Flow: Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration [14.194086645453767]
  Cross-pixel image registration is challenging due to severe non-linear radiometric and uncertainty.<n>In this paper we propose a novel framework that reformulates dense-modal flow estimation.
  arXiv  Detail & Related papers  (2026-06-29T15:58:25Z)
• ReFPO: Reflow Regularization for Flow Matching Policy Gradients [58.32178725687043]
  We present a simple online RL method that adds explicit Reflow regularization to Flow Matching Policy Gradients.<n>We experimentally demonstrate that ReFPO improves average performance and discretization across GridWorld, MuJoCo Playground, and high-dimensional Humanoid Control tasks.
  arXiv  Detail & Related papers  (2026-06-19T04:23:10Z)
• Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models [61.74572554094633]
  We argue that ratio clipping is structurally ill-suited for flow models.<n>We propose Flow-DPPO, which replaces ratio clipping with a divergence proximal constraint.<n> Experiments show that Flow-DPPO achieves higher rewards with better KL-proximal efficiency.
  arXiv  Detail & Related papers  (2026-06-09T15:59:57Z)
• A Learning-Based Superposition Operator for Non-Renewal Arrival Processes in Queueing Networks [0.0]
  Superposition of arrival processes is a fundamental yet analytically intractable operation in queueing networks.<n>We propose a scalable data-driven operator that maps low-order moments and autocorrelation descriptors of multiple arrival streams to those of their merged process.
  arXiv  Detail & Related papers  (2026-03-11T13:46:32Z)
• 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)
• Adaptive Benign Overfitting (ABO): Overparameterized RLS for Online Learning in Non-stationary Time-series [0.0]
  ABO is highly accurate (comparable to baseline kernel methods) while achieving speed improvements of between 20 and 40 percent.<n>Results provide a unified view linking adaptive filtering, kernel approximation, and benign overfitting within a stable online learning framework.
  arXiv  Detail & Related papers  (2026-01-29T15:58:01Z)
• Physics-Informed Design of Input Convex Neural Networks for Consistency Optimal Transport Flow Matching [1.3709465727733763]
  A physics-informed neural input consistency network (PICNN) plays a central role in constructing the flow field that emulates the displacement.<n>During the prediction stage, our approach supports both one-step (Mrenier-map) and multi-step ODE sampling from the same learned potential, leveraging the straightness of the OT flow.
  arXiv  Detail & Related papers  (2025-11-08T15:30:55Z)
• Iterative Refinement of Flow Policies in Probability Space for Online Reinforcement Learning [56.47948583452555]
  We introduce the Stepwise Flow Policy (SWFP) framework, founded on the key insight that discretizing the flow matching inference process via a fixed-step Euler scheme aligns it with the variational Jordan-Kinderlehrer-Otto principle from optimal transport.<n>SWFP decomposes the global flow into a sequence of small, incremental transformations between proximate distributions.<n>This decomposition yields an efficient algorithm that fine-tunes pre-trained flows via a cascade of small flow blocks, offering significant advantages.
  arXiv  Detail & Related papers  (2025-10-17T07:43:51Z)
• Conditional diffusions for amortized neural posterior estimation [8.37884129644711]
  We show the effectiveness of conditional diffusions coupled with high-capacity summary networks for amortized Neural posterior estimation.<n>Our results show improved stability, superior accuracy, and faster training times, even with simpler, shallower models.
  arXiv  Detail & Related papers  (2024-10-24T19:13:13Z)
• Stream-level flow matching with Gaussian processes [4.935875591615496]
  Conditional flow matching (CFM) is a family of training algorithms for fitting continuous normalizing flows (CNFs)<n>We extend the CFM algorithm by defining conditional probability paths along streams'', instances of latent paths that connect data pairs of source and target.<n>We show that this generalization of the CFM can effectively reduce the variance in the estimated marginal vector field at a moderate computational cost.
  arXiv  Detail & Related papers  (2024-09-30T15:47:22Z)
• 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)
• GMFlow: Learning Optical Flow via Global Matching [124.57850500778277]
  We propose a GMFlow framework for learning optical flow estimation. It consists of three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for global feature matching, and a self-attention layer for flow propagation. Our new framework outperforms 32-iteration RAFT's performance on the challenging Sintel benchmark.
  arXiv  Detail & Related papers  (2021-11-26T18:59:56Z)
• FPCR-Net: Feature Pyramidal Correlation and Residual Reconstruction for Optical Flow Estimation [72.41370576242116]
  We propose a semi-supervised Feature Pyramidal Correlation and Residual Reconstruction Network (FPCR-Net) for optical flow estimation from frame pairs. It consists of two main modules: pyramid correlation mapping and residual reconstruction. Experiment results show that the proposed scheme achieves the state-of-the-art performance, with improvement by 0.80, 1.15 and 0.10 in terms of average end-point error (AEE) against competing baseline methods.
  arXiv  Detail & Related papers  (2020-01-17T07:13:51Z)

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.