6 papers
Divergence-Suppressing Couplings for Rectified Flow
Yimeng Min, Carla P. Gomes
The promise of Rectified Flow rests on producing self-generated couplings whose trajectories are straight, or nearly so. In practice, trajectories generated by the base flow model…
Learning Unbiased Permutations via Flow Matching
Yimeng Min, Carla P. Gomes
Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution…
Graph Neural Networks are Heuristics
Yimeng Min, Carla P. Gomes
Graph neural networks are usually treated as auxiliaries for combinatorial optimization: they imitate algorithms, guide search, or supply scores to classical procedures. We show th…
Unsupervised Learning for Quadratic Assignment
Yimeng Min, Carla P. Gomes
We introduce PLUME search, a data-driven framework that enhances search efficiency in combinatorial optimization through unsupervised learning. Unlike supervised or reinforcement l…
Permutation Picture of Graph Combinatorial Optimization Problems
Yimeng Min
This paper proposes a framework that formulates a wide range of graph combinatorial optimization problems using permutation-based representations. These problems include the travel…
Comment on paper: Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
Yimeng Min
We identify two major issues in the SoftDist paper (Xia et al.): (1) the failure to run all steps of different baselines on the same hardware environment, and (2) the use of incons…