AI Paper Atlas

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

Rankmax: An Adaptive Projection Alternative to the Softmax Function

Weiwei Kong, Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Li Zhang

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 10 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 Softmax cross-entropy with Rankmax adaptive projection lossmulti-label retrieval model · MovieLens 20MAP@10: 0.182 -> 0.210Improved
replace Softmax with Rankmaxmulti-label retrieval model · MovieLens 20MAccuracy: 0.342 -> 0.397Improved
replace Sparsemax with Rankmaxmulti-label retrieval model · MovieLens 20MR@100: 0.464 -> 0.492Improved
replace Softmax with Rankmaxmulti-label retrieval model · MovieLens 100KAP@10 / Accuracy / R@100: AP@10 0.147 -> 0.154; R@100 0.401 -> 0.387Mixed
replace Softmax with Rankmaxmulti-label retrieval model · MovieLens 1BR@1000: 0.0117 -> 0.0116No clear effect
add exponential temperature annealing to SoftmaxSoftmax loss · MovieLens 20Mretrieval metricsNo clear effect

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