AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Scalable Distributional Robustness in a Class of Non-Convex Optimization with Guarantees

Avinandan Bose, Arunesh Sinha, Tien Anh Mai

NeurIPS 2022 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 1 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 stratified sampling instead of k-means clustering for abstractionMISOCP DRO · Synthetic SSG, S=24% of OPT: 94.03 -> 99.25Improved
Use stratified sampling (2 per strata) instead of clustering at small sample sizeMISOCP DRO · Synthetic SSG, S=8% of OPT: 80.17 -> 91.78Improved
Increase samples S from 8 to 24 with clustering (ablation)Clustering abstraction · Synthetic SSG% of OPT: 80.17 -> 94.03Improved
Increase samples per stratum from 2 to 4 at S=8 (ablation)Stratified sampling · Synthetic SSG, S=8% of OPT: 91.78 -> 78.89Hurt
Use clustering instead of PGA at high regularization xi=1E6MISOCP DRO · Synthetic SSG, N=500, M=10% of OPT: 49.2 -> 99.6Improved
Use clustering instead of TT-GAD at xi=1E6MISOCP DRO · Synthetic SSG, N=500, M=10% of OPT: 82.6 -> 99.6Improved
Use clustering instead of gradient baselines at low regularization xi=1E3MISOCP DRO · Synthetic SSG% of OPT: 99.8 -> 99.9No clear effect
Increase regularization xi from 1E3 to 1E6 for PGA (ablation)PGA baseline · Synthetic SSG% of OPT: 98.9 -> 49.2Hurt
Increase regularization xi from 1E3 to 1E6 for clustering (ablation)Clustering abstraction · Synthetic SSG% of OPT: 99.9 -> 99.6No clear effect
Increase number of alternatives M from 10 to 50 for PGA (ablation)PGA baseline · Synthetic SSG% of OPT: 49.2 -> 93.5Improved
Use sampling instead of PGA at M=50MISOCP DRO · Synthetic SSG% of OPT: 93.5 -> 99.5Improved
Use robust DRO (xi=1E2) instead of ERM for lowest-5% clientsMC-FCP m=10 · P&R-NYC testavg choice probability (H): 0.150 -> 0.417Improved

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