A Nearly-Optimal Bound for Fast Regression with $\ell_∞$ Guarantee

Authors: Zhao Song, Mingquan Ye, Junze Yin, Lichen Zhang

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical On the algorithmic side, we prove that there exists a distribution of dense sketching matrices with m = ϵ 2d log3(n/δ) such that solving the sketched regression problem gives the ℓ guarantee, with probability at least 1 δ. Moreover, we develop a novel analytical framework for ℓ guarantee regression that utilizes the Oblivious Coordinate-wise Embedding (OCE) property introduced in (Song & Yu, 2021). Our analysis is much simpler and more general than that of (Price et al., 2017).
Researcher Affiliation Collaboration 1Adobe Research 2University of Illinois at Chicago 3Boston University 4MIT.
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating that source code for the described methodology is publicly available.
Open Datasets No The paper is theoretical and does not discuss the use of any specific datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not discuss dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details such as hyperparameters or training configurations.