arXiv Machine Learning

Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets

The paper introduces a method for tackling combinatorial optimization (CO) problems—often NP‑hard—by leveraging GFlowNets to sample solutions from the solution space. It designs Markov decision processes tailored to various CO tasks and trains conditional GFlowNets, incorporating efficient training techniques for long‑range credit assignment. Experiments on synthetic and realistic datasets show that these GFlowNet policies can efficiently locate high‑quality solutions, and the implementation is publicly available.

arXiv Machine Learning

4d ago

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

arXiv Machine Learning

Jun 10

Latent Guided Sampling for Combinatorial Optimization

arXiv:2506. 03672v2 Announce Type: replace-cross Abstract: Combinatorial Optimization problems are widespread in domains such as logistics, manufacturing, and drug discovery, yet their NP-hard nature makes them computationally challenging.

By Sobihan Surendran (LPSM), Adeline Fermanian (LPSM), Sylvain Le Corff (LPSM)

diffusion reinforcement-learning benchmarks

arXiv Machine Learning

Jun 5

Your GFlowNet Secretly Learns an Optimal Transport Plan

arXiv:2606. 06272v1 Announce Type: new Abstract: Generative Flow Networks (GFlowNets) are a framework for sampling structured objects via stochastic trajectories in a directed graph.

By Ian Maksimov, Nikita Morozov, Denis Belomestny, Sergey Samsonov

arXiv Machine Learning

Jun 2

Regularized Large Neighborhood Search

arXiv:2606. 02294v1 Announce Type: new Abstract: Operations research practitioners typically tackle NP-hard combinatorial problems using large neighborhood search (LNS), a scalable heuristic that iteratively refines a current solution by locally re-optimizing subsets of its variables.

By Germain Vivier-Ardisson, Laurent Demonet, Axel Parmentier, Mathieu Blondel

arXiv AI

Jun 16

Proximal Policy Optimization for Amortized Discrete Sampling

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

reinforcement-learning benchmarks

arXiv AI

Aug 21

Learning Early-to-Final Solution Consistency for MILP Acceleration

arXiv:2608. 19953v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) is a fundamental problem class in operations research and combinatorial optimization, with broad applications to industrial decision-making.

By Guanlin Li, Chengrui Gao, Chenguang Wang, Haopu Shang, Zherong Zhang, Ke Xue, Jixiang Lu, Weiyong Yang, Chao Qian

benchmarks

arXiv AI

Jun 24

FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction

arXiv:2606. 24679v1 Announce Type: cross Abstract: Data preparation pipelines improve data quality in machine learning by transforming raw tables into learning-ready data through sequential cleaning and feature transformation operators.

By Kunyu Ni, Lei Cao, Jie He, Xiaotong Zhang, Jianfeng Jin, Junyu Dong, Yanwei Yu

llms benchmarks data-engineering

Hugging Face Trending Papers

Aug 20

Learning Early-to-Final Solution Consistency for MILP Acceleration

Mixed-Integer Linear Programming (MILP) is a fundamental problem class in operations research and combinatorial optimization, with broad applications to industrial decision-making. Owing to their NP-hardness, however, modern solvers may struggle to find high-quality solutions for challenging MILP instances within practical time limits.

benchmarks

arXiv Machine Learning

Aug 6

GFlowNet Training by Policy Gradients

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

reinforcement-learning

arXiv Machine Learning

Jun 18

FORGE: Foundational Optimization Representations from Graph Embeddings

arXiv:2508. 20330v5 Announce Type: replace Abstract: Combinatorial optimization problems are ubiquitous in science and engineering.

By Zohair Shafi, Serdar Kadioglu

rag fine-tuning efficiency benchmarks

arXiv Machine Learning

Jun 9

Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions

arXiv:2601. 22211v2 Announce Type: replace Abstract: Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical.

By Lingkai Kong, Anagha Satish, Hezi Jiang, Akseli Kangaslahti, Andrew Ma, Wenbo Chen, Mingxiao Song, Lily Xu, Milind Tambe

diffusion reinforcement-learning benchmarks

arXiv AI

Jun 15

Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning

arXiv:2509. 18930v3 Announce Type: replace-cross Abstract: Neural algorithmic reasoning (NAR) is a paradigm that trains neural networks to execute classic algorithms by supervised learning.

By Alex Schutz, Victor-Alexandru Darvariu, Efimia Panagiotaki, Bruno Lacerda, Nick Hawes

reinforcement-learning

Related stories