AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Data Amplification: A Unified and Competitive Approach to Property Estimation

Yi Hao, Alon Orlitsky, Ananda Theertha Suresh, Yihong Wu

NeurIPS 2018 · Learning theory and algorithms › Sample complexity · approach: Density and property estimation · 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
Use f* with 2n samples instead of the empirical estimator with n\log^{1/2-\epsilon}n samplesProperty estimators satisfying the paper's smoothness conditions · All underlying distributionsestimation loss: L_{f^*}(p, 2n) \le \left(1+\frac{3}{\log^{\epsilon}n}\right)L_{f^E}(p, n \log^{\frac{1}{2}-\epsilon}n)+C_f\min\left\{ \fImproved
Use f* with n samples rather than f^E with n\sqrt{\log n} samplesEntropy, support size, support coverage, power sums, and distance to uniformity · Six tested distributions per propertymean squared error: n\sqrt{\log n}Improved
Use f* instead of the best previous estimatorFive symmetric properties · Tested distributions, with uniform and near-uniform Dirichlet exceptions for PMLmean squared errorMixed
Use f* rather than estimators optimized for worst-case distributionsProperty estimation · More-skewed distributionsrelative efficacyImproved
Use f* rather than the empirical estimatorNormalized support size · Tested distributions, except near-uniform cases where PML performs bettermean squared errorImproved

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