AI Paper Atlas

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

On Tractable Computation of Expected Predictions

Pasha Khosravi, YooJung Choi, Yitao Liang, Antonio Vergari, Guy Van den Broeck

NeurIPS 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Data attribution and recourse · 23 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
Compute exact expected regression predictions instead of imputing missing featuresRegression circuits with probabilistic circuits · Abalone, Delta-Airloins, Elevators, InsuranceRMSEImproved
Approximate expected classifier predictions with a first-order Taylor expansionLogistic circuits with probabilistic circuits · MNIST, FashionaccuracyImproved
Require the regression and probabilistic circuits to share a vtreeRegression circuit moment computation · Circuit pairs with a shared vtreecomputational tractabilityImproved
Use regression circuits without a shared vtreeRegression circuit moment computation · Circuit pairs with arbitrary vtreescomputational tractabilityHurt
Apply a sigmoid to the regression circuit output for classificationLogistic circuits with probabilistic circuits · Expected classifier predictioncomputational tractabilityHurt

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