Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.18167 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912726028124160 |
|---|---|
| author | Qiao, Tianqi Maros, Marie |
| author_facet | Qiao, Tianqi Maros, Marie |
| contents | We propose and analyze a variant of Sparse Polyak for high dimensional M-estimation problems. Sparse Polyak proposes a novel adaptive step-size rule tailored to suitably estimate the problem's curvature in the high-dimensional setting, guaranteeing that the algorithm's performance does not deteriorate when the ambient dimension increases. However, convergence guarantees can only be obtained by sacrificing solution sparsity and statistical accuracy. In this work, we introduce a variant of Sparse Polyak that retains its desirable scaling properties with respect to the ambient dimension while obtaining sparser and more accurate solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18167 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sparse Polyak with optimal thresholding operators for high-dimensional M-estimation Qiao, Tianqi Maros, Marie Machine Learning Optimization and Control We propose and analyze a variant of Sparse Polyak for high dimensional M-estimation problems. Sparse Polyak proposes a novel adaptive step-size rule tailored to suitably estimate the problem's curvature in the high-dimensional setting, guaranteeing that the algorithm's performance does not deteriorate when the ambient dimension increases. However, convergence guarantees can only be obtained by sacrificing solution sparsity and statistical accuracy. In this work, we introduce a variant of Sparse Polyak that retains its desirable scaling properties with respect to the ambient dimension while obtaining sparser and more accurate solutions. |
| title | Sparse Polyak with optimal thresholding operators for high-dimensional M-estimation |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2511.18167 |