发表机构
Institute of Industrial Artificial Intelligence, CAS（中国科学院工业人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ORDO是面向MIP预求解的操作级回合感知动态排序框架，将预求解规划转化为自回归序列生成，实现跨域零样本加速，通过序列竞跑部署，为MIP预求解提供了新的动作排序方案。
AI 中文摘要
预求解对混合整数规划（MIP）性能有重要影响，但基于学习的方法仅优化参数配置，无法表达动作间非交换的时间依赖关系，其默认顺序在大多数领域几乎是唯一的，但功能上是必要的：人为打乱相同序列的顺序会使求解时间分布的尾部膨胀多达数倍。我们将预求解规划重新表述为在统一原子动作空间上的自回归序列生成，将决策对象转移到动作序列；我们将此框架命名为ORDO——面向MIP预求解的操作级回合感知动态排序。其优势在于跨域泛化：在多个未见过的领域上，它实现了端到端零样本加速——据我们所知，这是预求解动作序列的首个此类加速——加速效果因领域而异，且无法用语料库丰富度解释，最强领域在加入序列竞跑后达到最大加速。部署使用序列竞跑，其中候选序列并行运行并保留获胜者，这通过修改SCIP源代码添加的执行与观测设施实现，该设施沿原生路径注入序列，并记录哪些动作实际执行以及在哪个回合执行。
英文摘要
Presolve strongly affects mixed-integer programming (MIP) performance, yet learning-based methods only optimize parameter configurations and cannot express the non-commutative temporal dependencies among actions, whose default order is nearly unique on most domains, yet functionally necessary: artificially shuffling the order of the same sequence inflates the tail of the solve-time distribution by up to several-fold. We recast presolve planning as autoregressive sequence generation over a unified atomic action space, moving the decision object to action sequences; we call this framework ORDO---Operation-level Round-aware Dynamic Ordering for MIP Presolve. Its payoff is cross-domain generalization: on multiple unseen domains it attains end-to-end zero-shot speedup---to our knowledge the first for presolve action sequences---varying by domain and not explained by corpus richness, the strongest domain reaching the largest speedup once racing is added. Deployment uses sequence racing, in which candidate sequences run concurrently and the winner is kept, enabled by an execution-and-observation facility, added by modifying the SCIP source, that injects sequences along the native path and records which actions actually execute and in which round.
