The paper introduces a new learning objective called trajectory balance for Generative Flow Networks (GFlowNets), aiming to improve credit assignment across long action sequences. It demonstrates that minimizing this objective yields a policy that samples exactly from the target distribution. Experiments on four domains show that trajectory balance enhances convergence, sample diversity, and robustness to long sequences and large action spaces.
By Esmeralda S. Whitammer, Moksh Jain, Emmanuel Bengio, Chen Sun, Yoshua Bengio
The paper introduces a data‑free learning objective called relative trajectory balance for training diffusion models to sample from a posterior defined by a diffusion prior and an arbitrary black‑box constraint or likelihood. It proves asymptotic correctness of this objective and demonstrates its use across vision, language, and multimodal tasks, including classifier guidance, language infilling, and text‑to‑image generation. Additionally, the method is applied to continuous control with a score‑based behavior prior, achieving state‑of‑the‑art results in offline reinforcement learning.
By Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Esmeralda S. Whitammer
arXiv:2606. 16073v1 Announce Type: new Abstract: Sampling from complex, unnormalized probability densities is a fundamental challenge in Bayesian inference and probabilistic modeling.
By Kirill Korolev, Nikita Morozov, Stepan Pavlenko, Esmeralda S. Whitammer, Sergey Samsonov
arXiv:2605. 01729v2 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets) learn to sample states proportional to an unnormalized reward.
By Zengxiang Lei, Ananth Shreekumar, Jonathan Rosenthal, Ruoyu Song, Alvaro A. Cardenas, Daniel J. Fremont, Dongyan Xu, Satish Ukkusuri, Z. Berkay Celik
arXiv:2408. 05885v3 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets) have been shown effective to generate combinatorial objects with desired properties.
By Puhua Niu, Shili Wu, Mingzhou Fan, Xiaoning Qian
arXiv:2210.00580v4 Announce Type: replace
Abstract: This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically used to m...
By Esmeralda S. Whitammer, Salem Lahlou, Tristan Deleu, Xu Ji, Edward Hu, Katie Everett, Dinghuai Zhang, Yoshua Bengio
CF‑VLA introduces a two‑stage coarse‑to‑fine approach for vision‑language‑action policies, replacing multi‑step sampling with a coarse initialization that constructs an action‑aware starting point and a single‑step refinement that corrects residual errors. The coarse stage learns a conditional posterior over endpoint velocity to transform Gaussian noise into a structured initialization, while the fine stage performs a fixed‑time refinement. Experiments on CALVIN and LIBERO demonstrate that CF‑VLA achieves a strong efficiency‑performance trade‑off, reducing action sampling latency by 75.4 % and achieving an 83.0 % real‑robot success rate, outperforming existing NFE=2 methods and matching or surpassing NFE=10 baselines.
By Fan Du, Feng Yan, Jianxiong Wu, Xinrun Xu, Weiye Zhang, Weinong Wang, Yu Guo, Bin Qian, Zhihai He, Fei Wang, Heng Yang
arXiv:2606. 15793v1 Announce Type: cross Abstract: This paper explores policy gradient algorithms for training stochastic policies to sample from structured discrete probability distributions under the Generative Flow Network (GFlowNet) framework.
By Anna Zykova-Myzina, Timofei Gritsaev, Daniil Tiapkin, Nikita Morozov
arXiv:2606. 30376v1 Announce Type: new Abstract: Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods.
By Zheming Fu, Ruizhe He, Wei Shang, Xiaoxiao Ma, Lei Wang, Chang Liu, Siming Fu
The paper investigates a natural gradient method based on the Fisher information matrix of state-action distributions, which follows a Fisher‑Rao gradient flow within the state-action polytope under a linear potential. It establishes linear convergence rates for Fisher‑Rao gradient flows of linear programs, with the rate tied to the program’s geometry, and provides improved error bounds for entropic regularization. Additionally, the authors extend their analysis to perturbed flows, proving sublinear convergence for both perturbed Fisher‑Rao and natural gradient flows, thereby encompassing state‑action natural policy gradients.
By Johannes M\"uller, Semih \c{C}ayc{\i}, Guido Mont\'ufar
arXiv:2512. 24780v2 Announce Type: replace Abstract: Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking.
By Alan Oursland
arXiv:2310.02423v3 Announce Type: replace
Abstract: We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call $\Delta$-amortized inference ($\D...
By Jean-Pierre Falet, Hae Beom Lee, Esmeralda S. Whitammer, Chen Sun, Dragos Secrieru, Thomas Jiralerspong, Dinghuai Zhang, Guillaume Lajoie, Yoshua Bengio