Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.13647 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918060264259584 |
|---|---|
| author | Even, Bertrand Giraud, Christophe Verzelen, Nicolas |
| author_facet | Even, Bertrand Giraud, Christophe Verzelen, Nicolas |
| contents | In many high-dimensional problems, like sparse-PCA, planted clique, or clustering, the best known algorithms with polynomial time complexity fail to reach the statistical performance provably achievable by algorithms free of computational constraints. This observation has given rise to the conjecture of the existence, for some problems, of gaps -- so called statistical-computational gaps -- between the best possible statistical performance achievable without computational constraints, and the best performance achievable with poly-time algorithms. A powerful approach to assess the best performance achievable in poly-time is to investigate the best performance achievable by polynomials with low-degree. We build on the seminal paper of Schramm and Wein (2022) and propose a new scheme to derive lower bounds on the performance of low-degree polynomials in some latent space models. By better leveraging the latent structures, we obtain new and sharper results, with simplified proofs. We then instantiate our scheme to provide computational lower bounds for the problems of clustering, sparse clustering, and biclustering. We also prove matching upper-bounds and some additional statistical results, in order to provide a comprehensive description of the statistical-computational gaps occurring in these three problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13647 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Computational lower bounds in latent models: clustering, sparse-clustering, biclustering Even, Bertrand Giraud, Christophe Verzelen, Nicolas Statistics Theory Machine Learning 62H30, 68Q17 In many high-dimensional problems, like sparse-PCA, planted clique, or clustering, the best known algorithms with polynomial time complexity fail to reach the statistical performance provably achievable by algorithms free of computational constraints. This observation has given rise to the conjecture of the existence, for some problems, of gaps -- so called statistical-computational gaps -- between the best possible statistical performance achievable without computational constraints, and the best performance achievable with poly-time algorithms. A powerful approach to assess the best performance achievable in poly-time is to investigate the best performance achievable by polynomials with low-degree. We build on the seminal paper of Schramm and Wein (2022) and propose a new scheme to derive lower bounds on the performance of low-degree polynomials in some latent space models. By better leveraging the latent structures, we obtain new and sharper results, with simplified proofs. We then instantiate our scheme to provide computational lower bounds for the problems of clustering, sparse clustering, and biclustering. We also prove matching upper-bounds and some additional statistical results, in order to provide a comprehensive description of the statistical-computational gaps occurring in these three problems. |
| title | Computational lower bounds in latent models: clustering, sparse-clustering, biclustering |
| topic | Statistics Theory Machine Learning 62H30, 68Q17 |
| url | https://arxiv.org/abs/2506.13647 |