AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

A First-Order Algorithmic Framework for Distributionally Robust Logistic Regression

JIAJIN LI, SEN HUANG, Anthony Man-Cho So

NeurIPS 2019 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 5 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 DRLR (κ = 7) instead of RLR (κ = ∞)Logistic regression · a1a and a2a test; MNIST binary test datasetsclassification accuracy: 83.82% -> 84.01%; 83.93% -> 84.24%; 99.45% -> 99.55%; 99.54% -> 99.75%; 98.86% -> 98.92%; 97.31% -> 97.40%; 97.45% -> 97Improved
Use a geometrically increasing penalty instead of a constant penalty (ablation)LP-ADMM · Synthetic (N=10000, d=100)CPU time: 19.75±3.74 -> 1.37±0.12Improved
Use adaptive rather than constant penalty (ablation)LP-ADMM · Synthetic, small instancessub-optimality gapNo clear effect
Use adaptive rather than constant penalty (ablation)LP-ADMM · Synthetic, large instancessub-optimality gapImproved
Use a first-order local model for the μ-update instead of the classic quadratic term (ablation)LP-ADMM · Synthetic β-subproblemsub-optimality gapImproved
Use LP-ADMM instead of SubGradient, PDHG, Linearized-ADMM, or Standard ADMMβ-subproblem · Synthetic and ill-conditioned real datasetssub-optimality gapImproved

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