AI Paper Atlas

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

Distributionally Robust Graphical Models

Rizal Fathony, Ashkan Rezaei, Mohammad Ali Bashiri, Xinhua Zhang, Brian Ziebart

NeurIPS 2018 · Learning theory and algorithms › Prediction and decision losses · approach: Losses for decision-making · 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
Train with AGM's loss-aligned adversarial objective instead of CRF trainingStructured prediction · Facial emotion intensity prediction, absolute unweighted lossloss: 0.34 -> 0.33Improved
Train with AGM's loss-aligned adversarial objective instead of CRF trainingStructured prediction · Facial emotion intensity prediction, weighted zero-one lossloss: 0.32 -> 0.28Improved
Train with AGM's loss-aligned adversarial objective instead of CRF trainingStructured prediction · Facial emotion intensity prediction, weighted absolute lossloss: 0.36 -> 0.29Improved
Train with AGM's loss-aligned adversarial objective instead of CRF trainingStructured prediction · Facial emotion intensity prediction, unweighted zero-one lossloss: 0.32 -> 0.34Hurt
Train with AGM's loss-aligned adversarial objective instead of CRF trainingStructured prediction · Facial emotion intensity prediction, squared unweighted lossloss: 0.38 -> 0.38No clear effect
Train with AGM's loss-aligned adversarial objective instead of CRF trainingStructured prediction · Facial emotion intensity prediction, average lossloss: 0.35 -> 0.33Improved
Train with AGM's loss-aligned adversarial objective instead of SSVM trainingStructured prediction · Facial emotion intensity prediction, absolute unweighted lossloss: 0.40 -> 0.33Improved
Train with AGM's loss-aligned adversarial objective instead of SSVM trainingStructured prediction · Facial emotion intensity prediction, squared unweighted lossloss: 0.40 -> 0.38Improved
Train with AGM's loss-aligned adversarial objective instead of SSVM trainingStructured prediction · Facial emotion intensity prediction, weighted zero-one lossloss: 0.29 -> 0.28Improved
Train with AGM's loss-aligned adversarial objective instead of SSVM trainingStructured prediction · Facial emotion intensity prediction, weighted absolute lossloss: 0.29 -> 0.29No clear effect
Train with AGM's loss-aligned adversarial objective instead of SSVM trainingStructured prediction · Facial emotion intensity prediction, weighted squared lossloss: 0.33 -> 0.36Hurt
Train with AGM's loss-aligned adversarial objective instead of CRF trainingStructured prediction · CoNLL 2005 semantic role labelingcost-sensitive loss: 0.19 -> 0.14Improved

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