An extension of McDiarmid's inequality
arXiv:1511.05240v437 citations
Originality Synthesis-oriented
AI Analysis
This provides a theoretical extension for concentration inequalities, which is incremental for researchers in probability and statistics.
The paper generalizes McDiarmid's inequality for functions with bounded differences on high-probability sets, showing concentration around conditional expectations, and extends these results to general metric spaces.
We generalize McDiarmid's inequality for functions with bounded differences on a high probability set, using an extension argument. Those functions concentrate around their conditional expectations. We further extend the results to concentration in general metric spaces.