AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

On Regularized Square-root Regression Problems: Distributionally Robust Interpretation and Fast Computations

Hong T.M. Chu, Kim-Chuan Toh, Yangjing Zhang

JMLR 2022 · Learning theory and algorithms › Optimal transport · approach: Sinkhorn and entropic OT algorithms · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use PPDNA instead of pADMMsquare-root sparse group Lasso solver · Example 3 (4000,6000), w=(0,1)running time (mm:ss): 30:00 -> 05Improved
use PPDNA instead of dADMMsquare-root sparse group Lasso solver · Example 3 (4000,6000), w=(0,1)running time (mm:ss): 16:50 -> 05Improved
use PPDNA instead of S-TISPsquare-root group Lasso solver · Example 3 (4000,6000), w=(0,1)running time (mm:ss): 12:51 -> 05Improved
use PPDNA instead of S-TISPsquare-root group Lasso solver · Example 1 (1000,6000), w=(0,1)running time (mm:ss): 04 -> 00Hurt
use PPDNA instead of pADMMsquare-root sparse group Lasso solver · Example 2 (10000,480), w=(0.5,0.5)running time (mm:ss): 05:29 -> 10Improved
use PPDNA instead of dADMMsquare-root sparse group Lasso solver · Example 4b (4000,6000), w=(0,1)running time (mm:ss): 03:11 -> 01:33Improved
use PPDNA instead of pADMMsquare-root fused Lasso solver · UCI housing, lambda=1running time (mm:ss): 25:01 -> 05Improved
use square-root loss instead of least squares losstuning parameter lambda · Example 3 simulation, N=100, n=150, varying sigmarunning time (mm:ss)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy