paper-with-me

Papers

Towards Distillation Guarantees under Algorithmic Alignment for Combinatorial Optimization

2026-05-19 · Thien Le, Melanie Weber arxiv

Distillation transfers knowledge from a large model trained on broad data to a smaller, more efficient model suitable for deployment. In structured prediction settings, prior knowledge about the task can guide the choice of a target architecture that is algorithmically aligned with the underlying problem. Building on recent learning-theoretic analyses of decision-tree (DT) distillation (Boix-Adsera, 2024), we study when distillation succeeds for combinatorial optimization tasks. We focus on the case where the target model is a graph neural network whose architecture is aligned with a dynamic programming (DP) algorithm for the task. Assuming that the source model is sufficiently rich, formalized through the linear representation hypothesis (LRH) (Elhage et al., 2022; Park et al., 2024), we show that the distillation problem can be solved efficiently in the complexity parameters of the DP transition function, represented as a DT. Our results provide a rigorous sufficient condition for successful distillation in the flavour of algorithmic alignment.

📄 PDF Abstract BibTeX arXiv:2605.20074

Code (0)

등록된 구현이 없습니다.

Tasks

Structured PredictionGraph Neural Network

Similar Papers 제목 키워드 기반

Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers

2025-01-18 · Xiaoyu Li, YIngyu Liang, Jiangxuan Long, Zhenmei Shi 외

Looped Transformers have shown exceptional neural algorithmic reasoning capability in simulating traditional graph algorithms, but their application to more complex structures like hypergraphs remains underexplored. Hype…

Combinatorial Optimization

Omnimodal Dataset Distillation via High-order Proxy Alignment

2026-04-12 · Yuxuan Gao, Xiaohao Liu, Xiaobo Xia, Tongliang Liu arxiv

Dataset distillation compresses large-scale datasets into compact synthetic sets while preserving training performance, but existing methods are largely restricted to single-modal or bimodal settings. Extending dataset d…

Compact Conformal Subgraphs

2026-02-07 · Sreenivas Gollapudi, Kostas Kollias, Kamesh Munagala, Aravindan Vijayaraghavan arxiv

Conformal prediction provides rigorous, distribution-free uncertainty guarantees, but often yields prohibitively large prediction sets in structured domains such as routing, planning, or sequential recommendation. We int…

Sequential Recommendation

ALP-KD: Attention-Based Layer Projection for Knowledge Distillation

2020-12-27 · Peyman Passban, Yimeng Wu, Mehdi Rezagholizadeh, Qun Liu

Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trus…

Knowledge Distillation

Robust Voting Rules from Algorithmic Robust Statistics

2021-12-13 · Allen Liu, Ankur Moitra

Maximum likelihood estimation furnishes powerful insights into voting theory, and the design of voting rules. However the MLE can usually be badly corrupted by a single outlying sample. This means that a single voter or …