AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Exponentiated Strongly Rayleigh Distributions

Zelda E. Mariet, Suvrit Sra, Stefanie Jegelka

NeurIPS 2018 · Learning theory and algorithms › Sample complexity · approach: Statistical-query lower bounds · 5 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
increase exponent p from 0.5 to 2 (ablation)E-DPP · Cancer outlier detectionAUC: 0.952 -> 0.965Improved
increase exponent p from 0.5 to 2 (ablation)E-DPP · Letter outlier detectionAUC: 0.780 -> 0.847Improved
increase exponent p from 0.5 to 2 (ablation)E-DPP · Speech outlier detectionAUC: 0.455 -> 0.445No clear effect
use E-DPP p=2 instead of LoOPE-DPP · Letter outlier detectionAUC: 0.907 -> 0.847Hurt
use HBOS instead of E-DPP p=2baseline · Letter outlier detectionAUC: 0.847 -> 0.622Hurt
larger exponent p=2 for Nystrom landmark selection vs DPP/unif/lev/reglevE-DPP · Ailerons, Bank32NH, CPU regressiontest errorImproved
proposal sampler instead of swapchainE-k-DPP sampling · mixing time vs kiterations to PSRF 1.05Improved
proposal sampler instead of swapchainE-k-DPP sampling · wall-clock time vs kruntime (s)Hurt

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