An Unsupervised Learning Framework Combined with Heuristics for the Maximum Minimal Cut Problem

1 code implementation • 16 Aug 2024 • Huaiyuan Liu, Xianzhang Liu, Donghua Yang, Hongzhi Wang, Yingchi Long, Mengtong Ji, Dongjing Miao, Zhiyu Liang

The unsupervised solver is inspired by a relaxation-plus-rounding approach, the relaxed solution is parameterized by graph neural networks, and the cost and penalty of MMCP are explicitly written out, which can train the model end-to-end.

Combinatorial Optimization valid

Data Debugging is NP-hard for Classifiers Trained with SGD

no code implementations • 2 Aug 2024 • Zizheng Guo, PengYu Chen, Yanzhang Fu, Dongjing Miao

(1) If the loss function and the dimension of the model are not fixed, Debuggable is NP-complete regardless of the training order in which all the training samples are processed during SGD.