AI Paper Atlas

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

Distributionally Robust Counterfactual Risk Minimization

Louis Faury, Ugo Tanielian, Elvis Dohmatob, Elena Smirnova, Flavian Vasile

AAAI 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 30 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 adaptive-temperature KL robust risk instead of POEMCRM policies · Sceneexpected Hamming loss: 1.157 -> 1.128Improved
Use adaptive-temperature KL robust risk instead of POEMCRM policies · Yeastexpected Hamming loss: 4.535 -> 4.553No clear effect
Use adaptive-temperature KL robust risk instead of POEMCRM policies · RCV1-Topicsexpected Hamming loss: 0.918 -> 0.783Improved
Use adaptive-temperature KL robust risk instead of POEMCRM policies · TMC2009expected Hamming loss: 2.191 -> 2.126Improved
Use fixed-temperature KL robust risk instead of POEMCRM policies · Sceneexpected Hamming loss: 1.157 -> 1.146Improved
Use fixed-temperature KL robust risk instead of POEMCRM policies · Yeastexpected Hamming loss: 4.535 -> 4.604Hurt
Use fixed-temperature KL robust risk instead of POEMCRM policies · RCV1-Topicsexpected Hamming loss: 0.918 -> 0.922Hurt
Use fixed-temperature KL robust risk instead of POEMCRM policies · TMC2009expected Hamming loss: 2.191 -> 2.136Improved
Use adaptive-temperature KL robust risk instead of POEMgreedy CRM policies · SceneHamming loss: 1.157 -> 1.128Improved
Use adaptive-temperature KL robust risk instead of POEMgreedy CRM policies · YeastHamming loss: 4.261 -> 4.271No clear effect
Use adaptive-temperature KL robust risk instead of POEMgreedy CRM policies · RCV1-TopicsHamming loss: 0.918 -> 0.779Improved
Use adaptive-temperature KL robust risk instead of POEMgreedy CRM policies · TMC2009Hamming loss: 2.190 -> 2.034Improved

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