Work

Sketching in Regression: Sketchy in Practice?

Year: 2026

Type: preprint

Abstract: The Johnson-Lindenstrauss (JL) lemma and its extensions provide tools for solving the $L_2$ regression problem in high-dimensional settings with $n>d$, by transforming a subspace of $\mathbb{R}^{n}$ to a subspace of $\mathbb{R}^{m}$, (where $m

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2611.02808

Authors: Das, Somarddha, Gupta, Soupayan Das, Goswami, Koustav

Institution: Indian Statistical Institute

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Indian Statistical Institute

OpenAlex ID: W7225146744

Cites: 18

Cited by:

Related to: 10