AI Paper Atlas

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

Incorporating Unlabeled Data into Distributionally Robust Learning

Charlie Frogner, Sebastian Claici, Edward Chien, Justin Solomon

JMLR 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 18 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
constrain adversary with unlabeled data instead of Wasserstein ball onlydistributionally robust logistic regression · UCI binary datasets, N_l up to 1000performance bound (likelihood)Improved
use strong prior on label probabilities instead of weak priorDRL with unlabeled data · UCI binary datasetsperformance boundImproved
choose epsilon by cross-validation in traditional Wasserstein DRLtraditional DRL · six UCI datasetsout-of-sample likelihoodMixed
vary radius epsilon in DRL with unlabeled dataDRL with unlabeled data · six UCI datasetsout-of-sample likelihoodNo clear effect
use distributionally robust heuristic instead of EMC, Min MC, Max MC for active learningDR active learning · 14 UCI datasetsarea under likelihood curve: outperform on 8 of 14 datasetsImproved
use distributionally robust heuristic instead of random samplingDR active learning · 14 UCI datasetsarea under likelihood curve: underperformed random on 5 of 14Mixed
use existing model change heuristics instead of random samplingEMC, Min MC, Max MC · 14 UCI datasetsarea under likelihood curve: underperform on 10 of 14Hurt
use strong prior instead of weak prior in DR active learningDR active learning · 14 UCI datasetsarea under likelihood curve: 69.8 -> 69.8No clear effect
use DR (strong) instead of Random on Letter (U/V)DR active learning · Letter (U/V)area under likelihood curve: 77.8 -> 82.3Improved
use DR (strong) instead of Random on MagicDR active learning · Magicarea under likelihood curve: 52.2 -> 43.1Hurt

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