paper-with-me

홈 › Papers

GFlowNet Foundations

2021-11-17 · Yoshua Bengio, Salem Lahlou, Tristan Deleu, Edward J. Hu, Mo Tiwari, Emmanuel Bengio

Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them approximately sample in proportion to a given reward function. In this paper, we show a number of additional theoretical properties of GFlowNets. They can be used to estimate joint probability distributions and the corresponding marginal distributions where some variables are unspecified and, of particular interest, can represent distributions over composite objects like sets and graphs. GFlowNets amortize the work typically done by computationally expensive MCMC methods in a single but trained generative pass. They could also be used to estimate partition functions and free energies, conditional probabilities of supersets (supergraphs) given a subset (subgraph), as well as marginal distributions over all supersets (supergraphs) of a given set (graph). We introduce variations enabling the estimation of entropy and mutual information, sampling from a Pareto frontier, connections to reward-maximizing policies, and extensions to stochastic environments, continuous actions and modular energy functions.

📄 PDF Abstract BibTeX arXiv:2111.09266

Code (2)

saleml/gfn pytorch
saleml/torchgfn pytorch

Tasks

Active Learning

Similar Papers 제목 키워드 기반

Generative Flow Networks: Theory and Applications to Structure Learning

2025-01-09 · Tristan Deleu

Without any assumptions about data generation, multiple causal models may explain our observations equally well. To avoid selecting a single arbitrary model that could result in unsafe decisions if it does not match real…

Sequential Decision MakingVariational Inference

GFlowNet Training by Policy Gradients

2024-08-12 · Puhua Niu, Shili Wu, Mingzhou Fan, Xiaoning Qian

Generative Flow Networks (GFlowNets) have been shown effective to generate combinatorial objects with desired properties. We here propose a new GFlowNet training framework, with policy-dependent rewards, that bridges kee…

Reinforcement Learning (RL)

Embarrassingly Parallel GFlowNets

2024-06-05 · Tiago da Silva, Luiz Max Carvalho, Amauri Souza, Samuel Kaski 외

GFlowNets are a promising alternative to MCMC sampling for discrete compositional random variables. Training GFlowNets requires repeated evaluations of the unnormalized target distribution or reward function. However, fo…

Improving GFlowNets with Monte Carlo Tree Search

2024-06-19 · Nikita Morozov, Daniil Tiapkin, Sergey Samsonov, Alexey Naumov 외

Generative Flow Networks (GFlowNets) treat sampling from distributions over compositional discrete spaces as a sequential decision-making problem, training a stochastic policy to construct objects step by step. Recent st…

Your GFlowNet Secretly Learns an Optimal Transport Plan

2026-06-04 · Ian Maksimov, Nikita Morozov, Denis Belomestny, Sergey Samsonov arxiv

Generative Flow Networks (GFlowNets) are a framework for sampling structured objects via stochastic trajectories in a directed graph. In this work, we establish a theoretical connection between non-acyclic GFlowNets and …