2000 character limit reached
An extension of McDiarmid's inequality (1511.05240v4)
Published 17 Nov 2015 in cs.LG, math.PR, math.ST, and stat.TH
Abstract: 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.
- B. Bollobás. The chromatic number of random graphs. Combinatorica, 8(1):49–55, 1988.
- O. Bousquet and A. Elisseeff. Algorithmic stability and generalization performance. In Proc. of NIPS (2001).
- Concentration of multivariate polynomials and its applications. Combinatorica, 20:417–434, 2000.
- M. D. Kirszbraun. Uber die zusammenziehende und lipschitzsche transformationen. Fund. Math, 22:77–108, 1934.
- A. Kontorovich. Concentration in unbounded metric spaces and algorithmic stability. In Proc. of ICML (2014).
- S. Kutin. Extensions to McDiarmid’s inequality when differences are bounded with high probability. Technical report, 2002.
- Michel Ledoux. Isoperimetry and Gaussian analysis. Springer Berlin Heidelberg, 1996.
- C. McDiarmid. On the method of bounded differences. Surveys in Combinatorics, 141:148–188, 1989.
- C. McDiarmid. Concentration. Probabilistic Methods for Algorithmic Discrete Mathematics, 16:195–248, 1998.
- E. J. McShane. Extension of range of functions. Bull. Amer. Math. Soc., 40(1):837–842, 1934.
- W. Schudy and M. Sviridenko. Concentration and moment inequalities for polynomials of independent random variables. In Proc. of SODA (2012).
- V. H. Vu. On the concentration of multivariate polynomials with small expectation. Random Structures and Algorithms, 16:344–363, 2000.
- V. H. Vu. Concentration of non-Lipschitz functions and applications. Random Structures and Algorithms, 20:262–316, 2002.
- L. Warnke. On the method of typical bounded differences. Combinatorics, Probability and Computing, pages 1–31, 8 2015.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.