paper-with-me

Papers

Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems

2024-06-02 · Yifan Xia, Xianliang Yang, Zichuan Liu, Zhihao Liu, Lei Song, Jiang Bian

Recent advancements in solving large-scale traveling salesman problems (TSP) utilize the heatmap-guided Monte Carlo tree search (MCTS) paradigm, where machine learning (ML) models generate heatmaps, indicating the probability distribution of each edge being part of the optimal solution, to guide MCTS in solution finding. However, our theoretical and experimental analysis raises doubts about the effectiveness of ML-based heatmap generation. In support of this, we demonstrate that a simple baseline method can outperform complex ML approaches in heatmap generation. Furthermore, we question the practical value of the heatmap-guided MCTS paradigm. To substantiate this, our findings show its inferiority to the LKH-3 heuristic despite the paradigm's reliance on problem-specific, hand-crafted strategies. For the future, we suggest research directions focused on developing more theoretically sound heatmap generation methods and exploring autonomous, generalizable ML approaches for combinatorial problems. The code is available for review: https://github.com/xyfffff/rethink_mcts_for_tsp.

📄 PDF Abstract BibTeX arXiv:2406.03503

Code (1)

xyfffff/rethink_mcts_for_tsp 공식 구현 pytorch

Tasks

Position

Methods 이 논문이 사용한 방법론

Heatmap 설명 없음

Similar Papers 제목 키워드 기반

Comment on paper: Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems

2024-06-11 · 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 inconsistent time measurements when comparing …

AllPosition

Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression

2026-06-02 · Artur Zagitov, Alexander Miasnikov, Maxim Krutikov, Vladimir Aletov 외 arxiv

Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints. Tensor decompositions have emerged as a promising direction, offering compact parameterizations well sui…

Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning

2026-03-28 · Maximilian Mordig, Andreas Opedal, Weiyang Liu, Bernhard Schölkopf arxiv

Curriculum learning (CL), motivated by the intuition that learning in increasing order of difficulty should ease generalization, is commonly adopted both in pre-training and post-training of large language models (LLMs).…

Reinforcement Learning

Rethinking Neural Operations for Diverse Tasks

2021-03-29 · NeurIPS 2021 12 · Nicholas Roberts, Mikhail Khodak, Tri Dao, Liam Li 외

An important goal of AutoML is to automate-away the design of neural networks on new tasks in under-explored domains. Motivated by this goal, we study the problem of enabling users to discover the right neural operations…

AutoMLImage ClassificationInductive BiasMusic Modeling+2

Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior

2025-01-31 · Tongda Xu, Xiyan Cai, Xinjie Zhang, Xingtong Ge 외

Recent advancements in diffusion models have been leveraged to address inverse problems without additional training, and Diffusion Posterior Sampling (DPS) (Chung et al., 2022a) is among the most popular approaches. Prev…

GPU