atlas

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

Sample Complexity of Automated Mechanism Design

NeurIPS 2016 · Learning theory and algorithms › Submodular and game algorithms · approach: Learned auction design · 30 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Restrict auction class from AMAs/VVCAs/lambda-auctions to mixed bundling auctions (MBAs), a one-parameter familymixed bundling auctions (MBAs) · theoretical sample complexity (n-bidder, m-item)pseudo-dimension / sample complexity of uniform convergenceHelped
Add item-specific reserve prices to MBAs (MBARPs)mixed bundling auctions with reserve prices · theoretical sample complexity (n-bidder, m-item)pseudo-dimensionHurt
Use bundle-specific reserve prices instead of item-specific reserve pricesMBARPs · theoretical sample complexitysample complexityHurt
Restrict AMA class to lambda-auctions (no bidder weights) and require samples to scale as n^mlambda-auctions · theoretical lower bound (additive valuations)sample complexity lower boundHurt
Restrict AMA class to VVCAsVVCAs · theoretical lower boundsample complexity lower boundHurt

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