← Back to all news
arXiv Machine Learning By Rui Hu, Yu Chen, Zhuoran Li, Longbo Huang

Towards Understanding the Training of GFlowNets: A Theoretical Perspective

Read the original on arXiv Machine Learning →

The paper presents a theoretical framework linking balance objectives in Generative Flow Networks (GFlowNets) to sampling accuracy. It establishes bounds on terminal symmetric KL divergence in terms of expected balance loss and shows how approximate stationarity controls distribution error, accounting for parameterization incompleteness. The authors prove finite‑time convergence rates under various sampling and backward‑policy regimes, clarifying the roles of coverage, parameterization, and moving components in GFlowNet training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 6

Stable GFlowNets with TV Monitoring and Probabilistic Guarantees

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
More like this →
arXiv Machine Learning
4d ago

Universality and Convergence of Generative Flows

The paper studies generative flows that sample from an unnormalized target by training a flow to satisfy a balance condition. It shows that the training loss can certify sampler accuracy, can be driven to zero, and quantifies how fast gradient descent converges, with explicit bounds depending on the backward policy and graph structure. The authors provide theoretical guarantees, test them on finite graphs, and certify each theorem using a Lean 4 development.

By Leo Brunswic
diffusion
More like this →
arXiv Machine Learning
Aug 31

Trajectory balance: Improved credit assignment in GFlowNets

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
diffusion
More like this →