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.
By Dinghuai Zhang, Hanjun Dai, Esmeralda S. Whitammer, Aaron Courville, Yoshua Bengio, Ling Pan
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)
arXiv:2501. 17377v4 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) has emerged as a promising approach for solving Combinatorial Optimization (CO) problems, such as the 3D Bin Packing Problem (3D-BPP), Traveling Salesman Problem (TSP), or Vehicle Routing Problem (VRP), but these neural solvers often exhibit brittleness when facing distribution shifts.
By Han Fang, Paul Weng, Yutong Ban
arXiv:2606. 00366v1 Announce Type: new Abstract: We consider the problem of generating a large collection of initial guesses for local minima of multimodal non-convex continuous optimization problems.
By Anjian Li, Bartolomeo Stellato, Ryne Beeson
arXiv:2507. 21449v2 Announce Type: replace-cross Abstract: Degeneracy is an inherent feature of the loss landscape of neural networks, but it is not well understood how stochastic gradient MCMC (SGMCMC) algorithms interact with this degeneracy.
By Rohan Hitchcock, Jesse Hoogland
GeoPAR is a geometry-guided parallel autoregressive reinforcement learning framework designed for large-scale multi-agent combinatorial optimization. It introduces a projection-window sparse geometry mechanism, sparse edge-biased attention, and cache-guided conflict-aware assignment to better model local geometric structures and reduce duplicate task selections. Experiments on heterogeneous vehicle routing and multi-depot pickup-and-delivery problems demonstrate improved zero-shot generalization, fewer rollout steps, and efficient inference.
By Wenjian Wu, Zesheng Jia, Jiaying Tang, Benyuan Yang, Jin Wang
arXiv:2609. 22752v1 Announce Type: new Abstract: Diffusion models have demonstrated strong power in generative modeling tasks across multiple domains, exhibiting a remarkable capability of learning complex distributions from samples.
By Yang Hu, Na Li
arXiv:2607. 22467v1 Announce Type: new Abstract: Data scarcity poses a fundamental challenge in training generative models to produce initial guesses for parametric optimization problems that are otherwise numerically expensive to solve.
By Anjian Li, Ryne Beeson
arXiv:2605. 09075v2 Announce Type: replace-cross Abstract: Although the Laplace approximation offers a simple route to uncertainty quantification in deep neural networks, its reliance on inverting large Hessian matrices has motivated a range of computationally feasible low-dimensional or sparse approximations.
By Swarnali Raha, Kshitij Khare, Rohit K Patra
arXiv:2505. 04757v2 Announce Type: replace Abstract: This paper introduces a novel approach to contextual stochastic optimization, integrating operations research and machine learning to address decision-making under uncertainty.
By Louis Bouvier, Thibault Prunet, Vincent Lecl\`ere, Axel Parmentier
arXiv:2503. 03137v3 Announce Type: replace Abstract: Constructive neural combinatorial optimization (NCO) offers a promising paradigm for solving vehicle routing problems (VRPs) by directly learning to construct approximate optimal solutions, thereby reducing reliance on expert knowledge for algorithm design.
By Changliang Zhou, Xi Lin, Zhenkun Wang, Qingfu Zhang
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