AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Convergence Guarantees for the Good-Turing Estimator

Amichai Painsky

JMLR 2022 · Learning theory and algorithms › Sample complexity · approach: Minimax estimation rates

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 Good-Turing instead of ML, Laplace, smooth GT or PMLoccupancy probability estimation · Zipf's law (s=1.01, m=10000), k=0 and k=1MSEImproved
use ML or PML instead of Good-Turing for larger koccupancy probability estimation · Zipf's law (m=10000), k=10MSEImproved
use the hybrid GT-ML estimatoroccupancy probability estimation · Zipf's law (m=10000), k=10MSE: equals ML for n < 317 and GT otherwiseImproved
use GT instead of PMLoccupancy probability estimation · Uniform distribution (m=10000), k=0MSEImproved
use GT (and hybrid GT-ML) instead of alternativesoccupancy probability estimation · Step distribution (m=10000)MSEImproved
use hybrid GT-ML estimatoroccupancy probability estimation · Hamilton corpus (m=3578), k=8MSE: equals ML for n < 181 and GT otherwiseImproved
use Laplace instead of GToccupancy probability estimation · Skin biota (m=1221, n<=100), k=1MSEHurt
use hybrid GT-ML estimatoroccupancy probability estimation · US Census last names (m=1000), k=8MSE: equals GT for n >= 182Improved
use simultaneous bound instead of marginal bound for GT-ML threshold (ablation)MSE bound for set of occupancy probabilities · Theoretical bound, K={0..n}MSE bound: optimal threshold less than 20 for n = 20,000Improved
restrict alphabet size to bounded m in the GT bound (ablation)Good-Turing MSE bound · Theoretical bound, varying m/nMSE boundImproved

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