Transforming Constraint Programs to Input for Local Search
Summary
This paper presents a method to automatically generate local search neighborhoods from constraint specifications using symmetry properties, evaluated on six optimization problems.
Similar Articles
Learning Local Constraints for Reinforcement-Learned Content Generators
This paper proposes a hybrid method combining Wave Function Collapse (WFC) and reinforcement learning to generate game levels that are both visually satisfying and playable, using WFC constraints to guide the RL agent.
Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design
This paper proposes Latent Heuristic Search (LHS), a framework that shifts heuristic discovery to a learned continuous latent manifold, using gradient-based optimization and normalizing flows to generate novel heuristics conditioned on large language models, achieving competitive results on TSP, CVRP, KSP, and Online Bin Packing.
Developing a Totally Unimodular Linear Program for Optimal Conformance Checking: When and Why It Complements A*
This paper introduces a totally unimodular linear programming reformulation for alignment-based conformance checking, which complements A* search by providing speedups for long traces with deviations. The approach achieves 38.6% average runtime savings with 96% selection accuracy.
Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers
Researchers introduce symmetry-compatible optimizers that respect the equivariance structures of neural network parameters, improving training stability and performance over traditional methods like Adam. The approach is validated on various language model architectures including Qwen3-0.6B, Gemma 3 1B, and OLMoE-1B-7B.
GLENS: Global Search via Learning from Solver Iterates with Diffusion Models
GLENS is a data-efficient global search method that uses diffusion models to generate diverse, high-quality initial guesses for local minima in non-convex optimization problems by leveraging intermediate solver iterates as free data augmentation.