Fully explicit large deviation inequalities for empirical processes with applications to information-based complexity
arXiv:1504.00143
Originality Synthesis-oriented
AI Analysis
Provides explicit bounds for empirical processes, benefiting researchers in probability and complexity theory.
The paper derives fully explicit large deviation inequalities for empirical processes indexed by VC classes and demonstrates their application to information-based complexity.
In the present paper we obtain fully explicit large deviation inequalities for empirical processes indexed by a Vapnik--Chervonenkis class of sets (or functions). Furthermore we illustrate the importance of such results for the theory of information-based complexity.