paper-with-me

Papers

Accelerating Diffusion-based Combinatorial Optimization Solvers by Progressive Distillation

2023-08-12 · Junwei Huang, Zhiqing Sun, Yiming Yang

Graph-based diffusion models have shown promising results in terms of generating high-quality solutions to NP-complete (NPC) combinatorial optimization (CO) problems. However, those models are often inefficient in inference, due to the iterative evaluation nature of the denoising diffusion process. This paper proposes to use progressive distillation to speed up the inference by taking fewer steps (e.g., forecasting two steps ahead within a single step) during the denoising process. Our experimental results show that the progressively distilled model can perform inference 16 times faster with only 0.019% degradation in performance on the TSP-50 dataset.

📄 PDF Abstract BibTeX arXiv:2308.06644

Code (0)

등록된 구현이 없습니다.

Tasks

Combinatorial OptimizationDenoising

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Unsupervised Diffusion Solver for Combinatorial Optimization via Combinatorial Adjoint Matching

2026-05-29 · Shengyu Feng, Tarun Suresh, Yiming Yang arxiv

Diffusion-based neural solvers have shown strong promise for combinatorial optimization (CO), but existing methods typically rely on supervised training with large collections of near-optimal solutions. In this work, we …

DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization

2023-02-16 · NeurIPS 2023 11 · Zhiqing Sun, Yiming Yang

Neural network-based Combinatorial Optimization (CO) methods have shown promising results in solving various NP-complete (NPC) problems without relying on hand-crafted domain knowledge. This paper broadens the current sc…

Combinatorial OptimizationDenoisingTraveling Salesman Problem

GRASP: Accelerating Shortest Path Attacks via Graph Attention

2023-10-12 · Zohair Shafi, Benjamin A. Miller, Ayan Chatterjee, Tina Eliassi-Rad 외

Recent advances in machine learning (ML) have shown promise in aiding and accelerating classical combinatorial optimization algorithms. ML-based speed ups that aim to learn in an end to end manner (i.e., directly output …

Combinatorial OptimizationGraph Attention

Deep Symbolic Optimization for Combinatorial Optimization: Accelerating Node Selection by Discovering Potential Heuristics

2024-06-14 · Hongyu Liu, Haoyang Liu, Yufei Kuang, Jie Wang 외

Combinatorial optimization (CO) is one of the most fundamental mathematical models in real-world applications. Traditional CO solvers, such as Branch-and-Bound (B&B) solvers, heavily rely on expert-designed heuristics, w…

Combinatorial OptimizationCPUGPU

CADO: From Imitation to Cost Minimization for Heatmap-based Solvers in Combinatorial Optimization

2026-02-09 · Hyungseok Song, Deunsol Yoon, Kanghoon Lee, Han-Seul Jeong 외 arxiv

Heatmap-based solvers have emerged as a promising paradigm for Combinatorial Optimization (CO). However, we argue that the dominant Supervised Learning (SL) training paradigm suffers from a fundamental objective mismatch…

Reinforcement Learning