Optimal Oblivious Subspace Embeddings with Near-optimal Sparsity
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913811508756480 |
|---|---|
| author | Chenakkod, Shabarish Dereziński, Michał Dong, Xiaoyu |
| author_facet | Chenakkod, Shabarish Dereziński, Michał Dong, Xiaoyu |
| contents | An oblivious subspace embedding is a random $m\times n$ matrix $Π$ such that, for any $d$-dimensional subspace, with high probability $Π$ preserves the norms of all vectors in that subspace within a $1\pmε$ factor. In this work, we give an oblivious subspace embedding with the optimal dimension $m=Θ(d/ε^2)$ that has a near-optimal sparsity of $\tilde O(1/ε)$ non-zero entries per column of $Π$. This is the first result to nearly match the conjecture of Nelson and Nguyen [FOCS 2013] in terms of the best sparsity attainable by an optimal oblivious subspace embedding, improving on a prior bound of $\tilde O(1/ε^6)$ non-zeros per column [Chenakkod et al., STOC 2024]. We further extend our approach to the non-oblivious setting, proposing a new family of Leverage Score Sparsified embeddings with Independent Columns, which yield faster runtimes for matrix approximation and regression tasks.
In our analysis, we develop a new method which uses a decoupling argument together with the cumulant method for bounding the edge universality error of isotropic random matrices. To achieve near-optimal sparsity, we combine this general-purpose approach with new traces inequalities that leverage the specific structure of our subspace embedding construction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_08773 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimal Oblivious Subspace Embeddings with Near-optimal Sparsity Chenakkod, Shabarish Dereziński, Michał Dong, Xiaoyu Data Structures and Algorithms Machine Learning Numerical Analysis Probability An oblivious subspace embedding is a random $m\times n$ matrix $Π$ such that, for any $d$-dimensional subspace, with high probability $Π$ preserves the norms of all vectors in that subspace within a $1\pmε$ factor. In this work, we give an oblivious subspace embedding with the optimal dimension $m=Θ(d/ε^2)$ that has a near-optimal sparsity of $\tilde O(1/ε)$ non-zero entries per column of $Π$. This is the first result to nearly match the conjecture of Nelson and Nguyen [FOCS 2013] in terms of the best sparsity attainable by an optimal oblivious subspace embedding, improving on a prior bound of $\tilde O(1/ε^6)$ non-zeros per column [Chenakkod et al., STOC 2024]. We further extend our approach to the non-oblivious setting, proposing a new family of Leverage Score Sparsified embeddings with Independent Columns, which yield faster runtimes for matrix approximation and regression tasks. In our analysis, we develop a new method which uses a decoupling argument together with the cumulant method for bounding the edge universality error of isotropic random matrices. To achieve near-optimal sparsity, we combine this general-purpose approach with new traces inequalities that leverage the specific structure of our subspace embedding construction. |
| title | Optimal Oblivious Subspace Embeddings with Near-optimal Sparsity |
| topic | Data Structures and Algorithms Machine Learning Numerical Analysis Probability |
| url | https://arxiv.org/abs/2411.08773 |