Research map / Optimization / Optimizers
Universal Representation of Generalized Convex Functions and their Gradients
Moeen Nehzati
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use a learned finitely Y-convex mechanism instead of separate posted pricing | single-buyer multi-good auction · Auction Setting A, n=12 goods | profit per good: 0.250 -> 0.353 | Improved |
| learned mechanism compared with the optimal Straight-Jacket auction | Learned Mechanism · Auction Setting A, n=12 goods | profit per good: 0.353 vs 0.361 (SJa) | No clear effect |
| scale the number of goods up to 250 with the learned mechanism | Learned Mechanism · Auction Setting A | profit per good: 0.412 (n=50) -> 0.450 (n=250) | Improved |
| increase number of goods in non-inner-product auction | Learned Mechanism · Auction Setting B (hinge surplus) | profit per good: 1.022 -> 1.253 | Improved |
| evaluate with softmax instead of hardmax at high temperature (ablation) | Learned Mechanism · evaluation | result quality | No clear effect |
| use negative quadratic cost instead of quadratic cost for transport | OT map via finitely Y-convex potential · mixture of measures OT | qualitative map displacement | Mixed |
Closest papers by meaning
- Learning Generalized Linear Programming Value Functions (NeurIPS 2024 · similarity 0.85)
- Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds (NeurIPS 2024 · similarity 0.85)
- A Universal Transfer Theorem for Convex Optimization Algorithms Using Inexact First-order Oracles (ICML 2024 · similarity 0.85)
- Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization (NeurIPS 2025 · similarity 0.85)
- GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent (NeurIPS 2024 · similarity 0.84)
- How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization (ICML 2024 · similarity 0.84)
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.
