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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use DRLR (κ = 7) instead of RLR (κ = ∞) | Logistic regression · a1a and a2a test; MNIST binary test datasets | classification 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% -> 97 | Improved |
| 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±0.12 | Improved |
| Use adaptive rather than constant penalty (ablation) | LP-ADMM · Synthetic, small instances | sub-optimality gap | No clear effect |
| Use adaptive rather than constant penalty (ablation) | LP-ADMM · Synthetic, large instances | sub-optimality gap | Improved |
| Use a first-order local model for the μ-update instead of the classic quadratic term (ablation) | LP-ADMM · Synthetic β-subproblem | sub-optimality gap | Improved |
| Use LP-ADMM instead of SubGradient, PDHG, Linearized-ADMM, or Standard ADMM | β-subproblem · Synthetic and ill-conditioned real datasets | sub-optimality gap | Improved |
Closest papers by meaning
- Wasserstein Logistic Regression with Mixed Features (NeurIPS 2022 · similarity 0.90)
- Wasserstein Distributionally Robust Optimization through the Lens of Structural Causal Models and Individual Fairness (NeurIPS 2024 · similarity 0.90)
- A Robust Learning Approach for Regression Models Based on Distributionally Robust Optimization (JMLR 2018 · similarity 0.89)
- Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization (AAAI 2024 · similarity 0.88)
- Outlier-Robust Distributionally Robust Optimization via Unbalanced Optimal Transport (NeurIPS 2024 · similarity 0.87)
- Universal generalization guarantees for Wasserstein distributionally robust models (ICLR 2025 · similarity 0.86)
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.
