AI Paper Atlas

Research map / Optimization / Optimizers

Implicit rate-constrained optimization of non-decomposable objectives

Abhishek Kumar, Harikrishna Narasimhan, Andrew Cotter

ICML 2021 · Optimization › Optimizers · approach: Differentiating through embedded optimization · 2 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
Optimize FNR directly while enforcing the target FPR using implicit thresholds rather than cross-entropy trainingCelebA attribute classification · High-cheekbones, FPR 1%FNR (%): 53.5 -> 46.9Improved
Use implicit thresholds instead of TFCO's constrained optimizerCelebA attribute classification · High-cheekbones, FPR 5%FNR (%): 30.1 -> 28.5Improved
Optimize partial ROC-AUC with ICO instead of cross-entropyCelebA image classification · Mean over 8 attributes, FPR range [0,5%]partial ROC-AUC: 74.7 -> 76.8Improved
Optimize partial ROC-AUC with ICO instead of TFCOBigEarthNet image classification · Mean over 5 labels, FPR range [0,5%]partial ROC-AUC: 66.2 -> 68.5Improved
Optimize high-recall PR-AUC directly with ICO instead of cross-entropyUCI Letter · Recall [0.95, 1]PR-AUC: 15.13 ± 0.86 -> 23.04 ± 0.77Improved
Optimize high-recall PR-AUC directly with ICO instead of TFCOUCI IJCNN1 · Recall [0.95, 1]PR-AUC: 26.14 ± 0.57 -> 27.28 ± 0.58Improved
Use ICO instead of TFCO for high-recall PR-AUCUCI Communities & Crime · Recall [0.95, 1]PR-AUC: 47.04 ± 0.97 -> 47.03 ± 1.08No clear effect
Use ICO rather than TFCO for partial ROC-AUCCelebA image classification · Mean over 8 attributes, FPR range [0,1%]partial ROC-AUC: 65.9 -> 66.1Mixed

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