AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Coresets for Wasserstein Distributionally Robust Optimization Problems

Ruomin Huang, Jiawei Huang, Wenjie Liu, Hu Ding

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 0 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 dual coreset sampling instead of uniform samplingWDRO logistic regression · Letter, c=1%worst-case risk: 0.72518 -> 0.68933Improved
use dual coreset sampling instead of uniform samplingWDRO SVM · Letter, c=1%worst-case risk: 0.68707 -> 0.67866Improved
use dual coreset sampling instead of uniform samplingWDRO Huber regression · Appliances Energy, c=1%worst-case risk: 28.57655 -> 28.57627Improved
use dual coreset instead of layer samplingWDRO logistic regression · Letter, c=10%worst-case risk: 0.60007 -> 0.60113No clear effect
use dual coreset instead of layer samplingWDRO SVM · Letter, c=2%worst-case risk: 0.58967 -> 0.59850Hurt
use importance sampling instead of uniform samplingWDRO logistic regression · Letter, c=2%worst-case risk: 0.64630 -> 0.65798Hurt
use importance sampling instead of uniform samplingWDRO SVM · Letter, c=1%worst-case risk: 0.68707 -> 0.66576Improved
increase compression rate c from 1% to 10%DualCore on WDRO logistic regression · Letterworst-case risk: 0.68933 -> 0.60113Improved
increase compression rate c from 1% to 10%DualCore on WDRO SVM · Letterworst-case risk: 0.67866 -> 0.51066Improved
dual coreset instead of uniform samplingWDRO logistic regression · MNIST 0 vs 1, c=0.5%test accuracy: 94.14 -> 94.37Improved
dual coreset instead of uniform samplingWDRO logistic regression · MNIST 0 vs 2, c=0.5%test accuracy: 87.1 -> 84.98Hurt
dual coreset instead of uniform samplingWDRO logistic regression · MNIST 2 vs 7, c=0.5%test accuracy: 78.54 -> 86.15Improved

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