AI Paper Atlas

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

Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation

Yacine Jernite, Anna Choromanska, David Sontag

ICML 2017 · Learning theory and algorithms › Prediction and decision losses · approach: Tree ensemble optimization · 12 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
Learn the tree structure jointly with representations instead of using a Huffman treeFastText-style hierarchical classifier · YFCC100M, embedding dimension 50P@1: 28.3 -> 31.6; 29.9 -> 32.1Improved
Learn the tree structure jointly with representations instead of using a Huffman treeFastText-style hierarchical classifier · YFCC100M, embedding dimension 200P@1: 35.8 -> 36.1; 36.4 -> 36.6Mixed
Increase tree arity from 2 to 5FastText-style hierarchical classifier · YFCC100M, embedding dimension 50P@1: 27.2 -> 28.3Improved
Increase tree arity from 5 to 20FastText-style hierarchical classifier · YFCC100MP@1: 28.3 -> 29.9; 35.8 -> 36.4Improved
Use the learned tree rather than a random treeHierarchical language model · Gutenbergperplexity: 160 -> 148Improved
Use the learned tree rather than a clustering-based treeHierarchical language model · Gutenbergperplexity: 212 -> 148Improved
Use the learned hierarchical model rather than flat soft-maxLanguage model · Gutenbergperplexity: 149 -> 148Improved
Use the learned hierarchical model rather than flat soft-maxLanguage model · Gutenbergtrain ms/batch: 12.5 -> 4.5Improved
Use the learned hierarchical model rather than flat soft-maxLanguage model · Gutenbergtest ms/batch: 6.9 -> 0.9Improved

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