AI Paper Atlas

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

Benefits of Permutation-Equivariance in Auction Mechanisms

Tian Qin, Fengxiang He, Dingfeng Shi, Wenbing Huang, Dacheng Tao

NeurIPS 2022 · Learning theory and algorithms › Submodular and game algorithms · approach: Learned auction design · 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
project RegretNet to permutation-equivariant RegretNet-PE (orbit averaging)RegretNet · 5x1 Uniformrevenue: 0.658 -> 0.677Improved
project RegretNet to permutation-equivariant RegretNet-PERegretNet · 2x1 Uniformex-post regret (x1e5): 17.4 -> 14.6Improved
project RegretNet to permutation-equivariant RegretNet-PERegretNet · 3x1 Uniformex-post regret (x1e5): 18.3 -> 16.4Improved
project RegretNet to permutation-equivariant RegretNet-PERegretNet · 5x1 Uniformgeneralization error (x1e5): 6.40 -> 5.10Improved
project RegretNet to permutation-equivariant RegretNet-PERegretNet · 3x1 Uniformgeneralization error (x1e5): 11.4 -> 10.2Improved
project RegretNet to permutation-equivariant RegretNet-PERegretNet · 2x2 Uniformrevenue: 0.870 -> 0.913Improved
project well-trained RegretNet post hoc (RegretNet-Test)RegretNet · 5x1 Uniformex-post regret (x1e5): 15.9 -> 6.50Improved
project well-trained RegretNet post hoc (RegretNet-Test)RegretNet · 3x1 Uniformex-post regret (x1e5): 18.3 -> 13.3Improved
project well-trained RegretNet post hoc (RegretNet-Test)RegretNet · 5x1 Uniformrevenue: 0.658 -> 0.658No clear effect
orbit averaging (RegretNet-PE) instead of parameter-sharing (EquivariantNet)EquivariantNet · 1x2 Uniformrevenue: 0.551 -> 0.563Improved
orbit averaging (RegretNet-PE) instead of parameter-sharing (EquivariantNet)EquivariantNet · 1x2 Uniformex-post regret: 0.00013 -> 0.00037Hurt
orbit averaging (RegretNet-PE) instead of parameter-sharing (EquivariantNet)EquivariantNet · 2x2 Uniformex-post regret: 0.00100 -> 0.00067Improved

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