KL divergence
Type: Concept
As of November 2026, KL divergence has been mentioned in one podcast episode on ICLR (May 2015). Used to measure the asymmetry between distributions in the Gaussian word embedding model.
In mathematical statistics, the Kullback–Leibler (KL) divergence, denoted , is a type of statistical distance: a measure of how much an approximating probability distribution Q is different from a true probability distribution P. Mathematically, it is defined as
| Mentioned in | 1 episode on 1 podcast (as of November 2026) |
|---|---|
| First heard | May 2015 on ICLR |
| Field | Information Theory |
Who talks about KL divergence on podcasts?
KL divergence came up; the most recent mention was May 2015 on ICLR.
- ICLR2015-luke-vilnis on ICLR (May 2015)