AI Paper Atlas

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

Learning from Aggregate Observations

Yivan Zhang, Nontawat Charoenphakdee, Zhenguo Wu, Masashi Sugiyama

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 5 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 maximum-likelihood classification directly from triplet comparisons instead of triplet-loss representation learning plus clusteringOurs, triplet comparison · MNISTaccuracy: 22.77 -> 94.94Improved
Use maximum-likelihood classification directly from triplet comparisons instead of triplet-loss representation learning plus clusteringOurs, triplet comparison · FMNISTaccuracy: 27.27 -> 81.49Improved
Use maximum-likelihood classification directly from triplet comparisons instead of triplet-loss representation learning plus clusteringOurs, triplet comparison · KMNISTaccuracy: 20.39 -> 81.94Improved
Use maximum-likelihood classification directly from pairwise similarities instead of contrastive representation learning plus clusteringOurs, pairwise similarity · MNISTaccuracy: 98.45 -> 98.84Improved
Use maximum-likelihood classification directly from pairwise similarities instead of contrastive representation learning plus clusteringOurs, pairwise similarity · FMNISTaccuracy: 88.49 -> 90.59Improved
Use maximum-likelihood classification directly from pairwise similarities instead of contrastive representation learning plus clusteringOurs, pairwise similarity · KMNISTaccuracy: 89.65 -> 93.45Improved
Learn from group means using the aggregate likelihood instead of treating the mean as each instance's labelOurs, mean observation, GBM · abaloneMSE: 7.89 -> 4.80Improved
Learn from group means using the aggregate likelihood instead of treating the mean as each instance's labelOurs, mean observation, GBM · airfoilMSE: 28.65 -> 4.63Improved
Learn from pairwise ranks with the Gaussian likelihood instead of RankNet's Gumbel modelOurs, rank observation, GBM · abaloneerror variance: 10.66 -> 5.04Improved
Learn from pairwise ranks with the Gaussian likelihood instead of RankNet's Gumbel modelOurs, rank observation, GBM · airfoilerror variance: 47.46 -> 6.18Improved

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