ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2206.10291
23
5

Algorithmic Gaussianization through Sketching: Converting Data into Sub-gaussian Random Designs

21 June 2022
Michal Derezinski
ArXivPDFHTML
Abstract

Algorithmic Gaussianization is a phenomenon that can arise when using randomized sketching or sampling methods to produce smaller representations of large datasets: For certain tasks, these sketched representations have been observed to exhibit many robust performance characteristics that are known to occur when a data sample comes from a sub-gaussian random design, which is a powerful statistical model of data distributions. However, this phenomenon has only been studied for specific tasks and metrics, or by relying on computationally expensive methods. We address this by providing an algorithmic framework for gaussianizing data distributions via averaging, proving that it is possible to efficiently construct data sketches that are nearly indistinguishable (in terms of total variation distance) from sub-gaussian random designs. In particular, relying on a recently introduced sketching technique called Leverage Score Sparsified (LESS) embeddings, we show that one can construct an n×dn\times dn×d sketch of an N×dN\times dN×d matrix AAA, where n≪Nn\ll Nn≪N, that is nearly indistinguishable from a sub-gaussian design, in time O(nnz(A)log⁡N+nd2)O(\text{nnz}(A)\log N + nd^2)O(nnz(A)logN+nd2), where nnz(A)\text{nnz}(A)nnz(A) is the number of non-zero entries in AAA. As a consequence, strong statistical guarantees and precise asymptotics available for the estimators produced from sub-gaussian designs (e.g., for least squares and Lasso regression, covariance estimation, low-rank approximation, etc.) can be straightforwardly adapted to our sketching framework. We illustrate this with a new approximation guarantee for sketched least squares, among other examples.

View on arXiv
Comments on this paper