AI Paper Atlas

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

Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences

Ikko Yamane, Junya Honda, Florian Yger, Masashi Sugiyama

ICML 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 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
Replace Naive with Joint-RRLow-quality image classification · MNISTaccuracy: 88.06% -> 96.34%Improved
Replace Naive with Joint-RRLow-quality image classification · Fashion-MNISTaccuracy: 73.12% -> 86.93%Improved
Replace Naive with Joint-RRLow-quality image classification · CIFAR-10accuracy: 48.35% -> 69.10%Improved
Replace Naive with Joint-RRLow-quality image classification · CIFAR-100accuracy: 19.97% -> 28.05%Improved
Replace Naive with Joint-RRLow-quality image classification · MNISTMSE: 0.184 -> 0.056Improved
Replace Naive with Joint-RRLow-quality image classification · Fashion-MNISTMSE: 0.417 -> 0.194Improved
Replace Naive with Joint-RRLow-quality image classification · CIFAR-10MSE: 0.778 -> 0.424Improved
Replace Naive with Joint-RRLow-quality image classification · CIFAR-100MSE: 0.935 -> 0.846Improved
Jointly train f and h instead of training them in two steps2Step-RR · MNISTaccuracy: 96.19% -> 96.34%No clear effect
Jointly train f and h instead of training them in two steps2Step-RR · Fashion-MNISTaccuracy: 85.53% -> 86.93%Improved
Jointly train f and h instead of training them in two steps2Step-RR · CIFAR-10accuracy: 67.60% -> 69.10%Improved
Jointly train f and h instead of training them in two steps2Step-RR · CIFAR-100accuracy: 27.43% -> 28.05%Improved

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