AI Paper Atlas

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

Loss Decomposition for Fast Learning in Large Output Spaces

Ian En-Hsu Yen, Satyen Kale, Felix Yu, Daniel Holtmann-Rice, Sanjiv Kumar, Pradeep Ravikumar

ICML 2018 · Learning theory and algorithms › Prediction and decision losses · approach: Approximate nearest neighbor indexing · 9 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
decomposed search (Decomp-MIPS) instead of plain MIPS for gradient approximationmax-margin loss training of last layer · MegaFace multiclasstest accuracy over training timeImproved
decomposed search (Decomp-MIPS) instead of plain MIPSmax-margin loss on WikiLSHTC · WikiLSHTC multilabeltraining accuracy per epochImproved
sampled softmax instead of search-based gradientssoftmax loss · MegaFace multiclasstest accuracy over training timeHurt
sampled softmax instead of search-based gradientssoftmax loss · WikiLSHTC multilabeltraining accuracyHurt
decomposed search with MIPS-based gradients on skip-gramskip-gram word embedding · BillionWskip-gram loss vs timeImproved

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