Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.07734 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914149997477888 |
|---|---|
| author | Hong, Shu Mei, Yongsheng Imani, Mahdi Lan, Tian |
| author_facet | Hong, Shu Mei, Yongsheng Imani, Mahdi Lan, Tian |
| contents | Bayesian optimization (BO) is a powerful framework for optimizing expensive black-box objectives, yet extending it to graph-structured domains remains challenging due to the discrete and combinatorial nature of graphs. Existing approaches often rely on either full graph topology-impractical for large or partially observed graphs-or incremental exploration, which can lead to slow convergence. We introduce a scalable framework for global optimization over graphs that employs low-rank spectral representations to build Gaussian process (GP) surrogates from sparse structural observations. The method jointly infers graph structure and node representations through learnable embeddings, enabling efficient global search and principled uncertainty estimation even with limited data. We also provide theoretical analysis establishing conditions for accurate recovery of underlying graph structure under different sampling regimes. Experiments on synthetic and real-world datasets demonstrate that our approach achieves faster convergence and improved optimization performance compared to prior methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07734 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Global Optimization on Graph-Structured Data via Gaussian Processes with Spectral Representations Hong, Shu Mei, Yongsheng Imani, Mahdi Lan, Tian Machine Learning Artificial Intelligence Social and Information Networks Signal Processing Bayesian optimization (BO) is a powerful framework for optimizing expensive black-box objectives, yet extending it to graph-structured domains remains challenging due to the discrete and combinatorial nature of graphs. Existing approaches often rely on either full graph topology-impractical for large or partially observed graphs-or incremental exploration, which can lead to slow convergence. We introduce a scalable framework for global optimization over graphs that employs low-rank spectral representations to build Gaussian process (GP) surrogates from sparse structural observations. The method jointly infers graph structure and node representations through learnable embeddings, enabling efficient global search and principled uncertainty estimation even with limited data. We also provide theoretical analysis establishing conditions for accurate recovery of underlying graph structure under different sampling regimes. Experiments on synthetic and real-world datasets demonstrate that our approach achieves faster convergence and improved optimization performance compared to prior methods. |
| title | Global Optimization on Graph-Structured Data via Gaussian Processes with Spectral Representations |
| topic | Machine Learning Artificial Intelligence Social and Information Networks Signal Processing |
| url | https://arxiv.org/abs/2511.07734 |