conftrace_

good-turing estimator

10 papers

Explore in graph

Co-occurring keywords · papers mentioning both

missing mass (2) heavy tail (2) absolute discounting (2) distribution estimation (2) mean squared error (2) minimax optimality (2) missing mass estimation (1) extreme value theory (1) n-gram language model (1) regular variation (1)

Papers

How Much is Unseen Depends Chiefly on Information About the Seen ICLR 2025 Just Wing It: Near-Optimal Estimation of Missing Mass in a Markovian Sequence JMLR 2024 Convergence Guarantees for the Good-Turing Estimator JMLR 2022 Consistent estimation of small masses in feature sampling JMLR 2021 Towards Competitive N-gram Smoothing AISTATS 2020 The power of absolute discounting: all-dimensional distribution estimation NeurIPS 2017 Competitive Distribution Estimation: Why is Good-Turing Good NeurIPS 2015 Optimal Discovery with Probabilistic Expert Advice: Finite Time Analysis and Macroscopic Optimality JMLR 2013 Rare Probability Estimation under Regularly Varying Heavy Tails COLT 2012 Concentration Bounds for Unigram Language Models JMLR 2005