AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Dimension Estimation Using Random Connection Models

Paulo Serra, Michel Mandjes

JMLR 2017 · Learning theory and algorithms › Sample complexity · approach: Density and property estimation

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 m_n from log(n) to n (ablation)canonical estimator · Sierpinski carpet, n=2560execution time multiplier: 638.54 times slowerHurt
increase m_n from log(n) to n (ablation)canonical estimator · Sierpinski carpet, n=2560percent of runs with true d within 2 sd: 84.95 -> 0.00Hurt
increase m_n from log(n) to n (ablation)canonical estimator · Sierpinski carpet, n=2560standard deviation of estimate: 0.22 -> 0.01Improved
increase m_n (log(n) to n) (ablation)canonical estimator · Sierpinski carpet, n=2560mean estimate (bias): 1.6790 -> 1.6772No clear effect
add multiplicative bias correction (ablation)canonical estimator · Gaussian design, d=10, n=10^7estimated dimension (true 10): 8.97 -> 9.74Improved
add exact g_eps(d) additive correction (ablation)canonical estimator · Gaussian design, d=10, n=10^7estimated dimension (true 10): 8.97 -> 9.39Improved
add two-standard-deviation shift (ablation)canonical estimator · Gaussian design, d=10, n=10^7estimated dimension (true 10): 8.97 -> 10.47Improved
use exact additive correction instead of multiplicative (ablation)bias-corrected estimator · Gaussian designestimated dimensionHurt
increase true dimension d to 10canonical estimator · Gaussian design, n=10^7estimated dimension: 10 -> 8.97Hurt
increase sample size n from 10^3 to 10^7 (ablation)canonical estimator · Gaussian design, d=10estimated dimension: 5.95 -> 8.97Improved
add noise dimensions (lower SNR)canonical estimator · Gaussian in R^5, n=10^5estimated dimensionMixed

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