AI Paper Atlas

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

AutoEncoder by Forest

Ji Feng, Zhi-Hua Zhou

AAAI 2018 · Learning theory and algorithms › Prediction and decision losses · approach: Tree ensemble optimization · 45 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 unsupervised rather than supervised tree construction (ablation)eForest · MNIST testMSE: 1386.96 -> 27.39 (500 trees); 701.99 -> 6.86 (1,000 trees)Improved
Use unsupervised rather than supervised tree construction (ablation)eForest · CIFAR-10 testMSE: 1623.93 -> 579.337 (500 trees); 567.64 -> 153.68 (1,000 trees)Improved
Increase the forest from 500 to 1,000 trees (ablation)eForest supervised · MNIST testMSE: 1386.96 -> 701.99Improved
Increase the forest from 500 to 1,000 trees (ablation)eForest unsupervised · MNIST testMSE: 27.39 -> 6.86Improved
Increase the forest from 500 to 1,000 trees (ablation)eForest supervised · CIFAR-10 testMSE: 1623.93 -> 567.64Improved
Increase the forest from 500 to 1,000 trees (ablation)eForest unsupervised · CIFAR-10 testMSE: 579.337 -> 153.68Improved
Use unsupervised rather than supervised tree construction (ablation)eForest · IMDB testcosine distance: 0.1132 -> 0.0070 (500 trees); 0.0676 -> 0.0023 (1,000 trees)Improved
Increase the forest from 500 to 1,000 trees (ablation)eForest unsupervised · IMDB testcosine distance: 0.0070 -> 0.0023Improved
Use eForest rather than MLP-AEauto-encoding · MNIST testMSE: 163.97 (MLP2) -> 6.86 (eForest unsupervised, 1,000 trees)Improved
Use eForest rather than MLP-AEauto-encoding · IMDB testcosine distance: 0.512 -> 0.0023Improved
Train a reusable eForest rather than an MLP-AEmodel reuse across datasets · CIFAR-10-trained model on MNIST testMSE: 1898.76 -> 90.43Improved
Train a reusable eForest rather than an MLP-AEmodel reuse across datasets · MNIST-trained model on Omniglot testMSE: 596.24 -> 12.80Improved

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