Name
Abstract | ||
|---|---|---|
For any memoryless communication channel with a binary-valued input and a one-dimensional real-valued output, we introduce a probabilistic lower bound on the mutual information given empirical observations on the channel. The bound is built on the Dvoretzky-Kiefer-Wolfowitz inequality and is distribution free. A quadratic time algorithm is described for computing the bound and its corresponding class-conditional distribution functions. We compare our approach to existing techniques and show the superiority of our bound to a method inspired by Fano’s inequality where the continuous random variable is discretized. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1162/NECO_a_00144 | Neural Computation |
Keywords | Field | DocType |
mutual information,conditional distribution,random variable,communication channels,lower bound | Sampling distribution,Chapman–Robbins bound,Random variable,Conditional probability distribution,Upper and lower bounds,Algorithm,Mutual information,Probabilistic logic,Time complexity,Mathematics | Journal |
Volume | Issue | ISSN |
23 | 7 | 0899-7667 |
Citations | PageRank | References |
1 | 0.40 | 13 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nathan D. VanderKraats | 1 | 1 | 0.40 |
| Arunava Banerjee | 2 | 313 | 29.18 |