|
|
|
|
|
|
by tonic_section
2102 days ago
|
|
|
The objective function used in these lossy neural compression schemes usually takes the form of a rate-distortion Lagrangian - the rate term captures the expected length of the message needed to transmit the compressed information and the distortion term measures the reconstruction error. So it wouldn't be able to cheat like in your example, because this would incur a high value of the loss through the rate term. |
|
|