AI Paper Atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

A Scalable Neural Network for DSIC Affine Maximizer Auction Design

Zhijian Duan, Haoran Sun, Yurong Chen, Xiaotie Deng

NeurIPS 2023 · Learning theory and algorithms › Submodular and game algorithms · approach: Learned auction design · 6 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
Learnable boost lambda instead of fixed lambda=0 (ablation)AMenuNet · 5x2 (B)average revenue: 0.3363 -> 0.7548Improved
Learnable boost lambda instead of fixed lambda=0 (ablation)AMenuNet · 3x2 (B)average revenue: 0.3892 -> 0.6197Improved
Learnable weights w instead of fixed w=1 (ablation)AMenuNet · 5x2 (B)average revenue: 0.7010 -> 0.7548Improved
Learnable weights w instead of fixed w=1 (ablation)AMenuNet · 2x10 (A)average revenue: 2.3848 -> 2.3815No clear effect
Learnable menu instead of all deterministic allocations (A_dtm) (ablation)AMenuNet · 2x2 (A)average revenue: 0.3633 -> 0.4293Improved
Learnable menu instead of all deterministic allocations (A_dtm) (ablation)AMenuNet · 2x10 (A) and 3x10 (C)average revenue: 59049 and 1048576 menu entriesImproved
Transformer-based architecture instead of 4-layer FCN (ablation)AMenuNet · 3x10 (C)average revenue: 5.0262 -> 5.5896Improved
Transformer-based architecture instead of 4-layer FCN (ablation)AMenuNet · 2x2 (A)average revenue: 0.4124 -> 0.4293Improved
Train AMenuNet on 2x5 and test on 2x10 (out-of-setting) vs Item-MyersonAMenuNet · 2x10 (A)average revenue: 2.1398 -> 2.2034Improved
Train on 2x2 and test on 2x5 (out-of-setting) vs Item-MyersonAMenuNet · 2x5 (A)average revenue: 1.0700 -> 1.0503Hurt
Train on 2x5 and test on 2x2 (smaller than training)AMenuNet · 2x2 (A)average revenue: 0.4265 -> 0.1212Hurt
Affine parameters (AMenuNet) added to VCGVCG · contextual 3x10 (A)average revenue: 2.2967 -> 2.9006Improved

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