AI Paper Atlas

Research map / Optimization / Optimizers

Universal Representation of Generalized Convex Functions and their Gradients

Moeen Nehzati

ICML 2026 · Optimization › Optimizers · approach: Differentiating through embedded optimization · 0 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 a learned finitely Y-convex mechanism instead of separate posted pricingsingle-buyer multi-good auction · Auction Setting A, n=12 goodsprofit per good: 0.250 -> 0.353Improved
learned mechanism compared with the optimal Straight-Jacket auctionLearned Mechanism · Auction Setting A, n=12 goodsprofit per good: 0.353 vs 0.361 (SJa)No clear effect
scale the number of goods up to 250 with the learned mechanismLearned Mechanism · Auction Setting Aprofit per good: 0.412 (n=50) -> 0.450 (n=250)Improved
increase number of goods in non-inner-product auctionLearned Mechanism · Auction Setting B (hinge surplus)profit per good: 1.022 -> 1.253Improved
evaluate with softmax instead of hardmax at high temperature (ablation)Learned Mechanism · evaluationresult qualityNo clear effect
use negative quadratic cost instead of quadratic cost for transportOT map via finitely Y-convex potential · mixture of measures OTqualitative map displacementMixed

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