Optimal testing of discrete distributions with high probability

Autor: John Peebles, Ilias Diakonikolas, Themis Gouleakis, Daniel M. Kane, Eric Price
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Computer Science - Machine Learning
sampling
Mathematics - Statistics Theory
Machine Learning (stat.ML)
Sample (statistics)
Statistics Theory (math.ST)
0102 computer and information sciences
02 engineering and technology
01 natural sciences
Machine Learning (cs.LG)
Total variation
Statistics - Machine Learning
Computer Science - Data Structures and Algorithms
FOS: Mathematics
0202 electrical engineering
electronic engineering
information engineering
Range (statistics)
Applied mathematics
Data Structures and Algorithms (cs.DS)
Statistical theory
distribution property testing
Mathematics
Sampling (statistics)
020206 networking & telecommunications
Function (mathematics)
high confidence
Distribution (mathematics)
010201 computation theory & mathematics
Constant (mathematics)
Zdroj: STOC
STOC '21
Popis: We study the problem of testing discrete distributions with a focus on the high probability regime. Specifically, given samples from one or more discrete distributions, a property $\mathcal{P}$, and parameters $0< \epsilon, \delta
Databáze: OpenAIRE
Externí odkaz: