4 papers · 1 filter
Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
Yudong W. Xu, Wenhao Li, Xiaoyu Wang +2
Diffusion models have shown promise in learning to solve constraint optimization problems. However, they are mostly restricted to problems with binary variables and rely on graph n…
Large Neighborhood Search meets Iterative Neural Constraint Heuristics
Yudong W. Xu, Wenhao Li, Scott Sanner +1
Neural networks are being increasingly used as heuristics for constraint satisfaction. These neural methods are often recurrent, learning to iteratively refine candidate assignment…
Reinforcement learning with combinatorial actions for coupled restless bandits
Lily Xu, Bryan Wilder, Elias B. Khalil +1
Reinforcement learning (RL) has increasingly been applied to solve real-world planning problems, with progress in handling large state spaces and time horizons. However, a key bott…
Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction
Yudong W. Xu, Wenhao Li, Scott Sanner +1
We present a Transformer-based framework for Constraint Satisfaction Problems (CSPs). CSPs find use in many applications and thus accelerating their solution with machine learning…