5,337
edits
Deep Learning: Difference between revisions
→Dequantization
| Line 1,473: | Line 1,473: | ||
This behavior is not specific to flow-based models. | This behavior is not specific to flow-based models. | ||
Suppose <math>P_{\theta}</math> is <math>N(0, I_d)</math>. | Suppose <math>P_{\theta}</math> is <math>N(0, I_d)</math>. | ||
Our typical example has <math>\Vert x_i \Vert^2 = O( | Our typical example has <math>\Vert x_i \Vert^2 = O(d)</math>. | ||
Consider <math>x^{test} = 0</math> then <math>P_{\theta}(x^{test}) > P_{\theta}(x_1)</math>. | Consider <math>x^{test} = 0</math> then <math>P_{\theta}(x^{test}) > P_{\theta}(x_1)</math>. | ||