Date
Thu, 20 Feb 2025
16:00
Location
L5
Speaker
Behnoosh Zamanlooy
Organisation
McMaster University

We investigate the strong data processing inequalities of contractive Markov Kernels under a specific f-divergence, namely the E-gamma-divergence. More specifically, we characterize an upper bound on the E-gamma-divergence between PK and QK, the output distributions of contractive Markov kernel K, in terms of the E-gamma-divergence between the corresponding input distributions P and Q. Interestingly, the tightest such upper bound turns out to have a non-multiplicative form. We apply our results to derive new bounds for the local differential privacy guarantees offered by the sequential application of a privacy mechanism to data and we demonstrate that our framework unifies the analysis of mixing times for contractive Markov kernels.

Further Information

Please join us outside the lecture room from 15:30 for refreshments.

Last updated on 12 Feb 2025, 7:55am. Please contact us with feedback and comments about this page.