AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

A Sample Complexity Measure with Applications to Learning Optimal Auctions

Vasilis Syrgkanis

NeurIPS 2017 · Learning theory and algorithms › Sample complexity · approach: Sample complexity of ranking and selection

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
Bound ERM generalization with the split-sample hypothesis space rather than the full hypothesis classGeneral ERM · General PAC learningexpected generalization error upper bound: \sqrt{\frac{2\log(\hat{\tau}_H(2m))}{m}}Improved
Choose reserve prices from observed valuationsERM reserve pricing · Single bidder, single itemexpected revenue loss upper bound: \sqrt{\frac{2\log(2m)}{m}}Improved
Choose a shared reserve from observed valuationsERM second-price auction · Multiple i.i.d. regular bidders, single itemexpected revenue loss upper bound: \sqrt{\frac{2\log(2\cdot n\cdot m)}{m}}Improved
Use player-specific reserves selected from observed valuesERM second-price auction · Non-i.i.d. regular bidders, single itemexpected revenue loss upper bound: \sqrt{\frac{2n\log(2m)}{m}}Improved
Coarsen virtual value functions to an epsilon gridERM over t-level auctions · Non-i.i.d. irregular bidders, single itemexpected revenue loss upper bound: 2\left(\frac{2n\log(2m)}{m}\right)^{1/3}Improved

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