论文信息 - Measure Concentration of Markov Tree Processes

Measure Concentration of Markov Tree Processes

We prove an apparently novel concentration of measure result for Markov tree processes. The bound we derive reduces to the known bounds for Markov processes when the tree is a chain, thus strictly generalizing the known Markov process concentration results. We employ several techniques of potential independent interest, especially for obtaining similar results for more general directed acyclic graphical models.

L. Kontorovich

[1] K. Ramanan,et al. Concentration Inequalities for Dependent Random Variables via the Martingale Method , 2006, math/0609835.

[2] L. Kontorovich. Metric and Mixing Sufficient Conditions for Concentration of Measure , 2006, math/0610427.

[3] L. Kontorovich. Measure Concentration of Hidden Markov Processes , 2006, math/0608064.

[4] A. Dembo,et al. A large-deviation theorem for tree-indexed Markov chains , 2003, math/0306045.

[5] M. Ledoux. The concentration of measure phenomenon , 2001 .

[6] CONCENTRATION OF MEASURE INEQUALITIES FOR MARKOV CHAINS AND -MIXING PROCESSES By Paul-Marie Samson , 2000 .

[7] Paul-Marie Samson,et al. Concentration of measure inequalities for Markov chains and $\Phi$-mixing processes , 2000 .

[8] K. Marton. A measure concentration inequality for contracting markov chains , 1996 .

[9] K. Marton. Bounding $\bar{d}$-distance by informational divergence: a method to prove measure concentration , 1996 .

[10] BOUNDING d - DISTANCE BY INFORMATIONAL DIVERGENCE: A METHOD TO PROVE MEASURE CONCENTRATION 1 , 2022 .