Perception-Distortion Trade-off with Restricted Boltzmann Machines
This work addresses missing data inference tasks, but it appears incremental as it applies a known trade-off to a specific method.
The authors tackled the problem of missing data inference using Restricted Boltzmann Machines by introducing a new linearization-based procedure, and they compared its performance with existing methods, placing the results within the perception-distortion trade-off context.
In this work, we introduce a new procedure for applying Restricted Boltzmann Machines (RBMs) to missing data inference tasks, based on linearization of the effective energy function governing the distribution of observations. We compare the performance of our proposed procedure with those obtained using existing reconstruction procedures trained on incomplete data. We place these performance comparisons within the context of the perception-distortion trade-off observed in other data reconstruction tasks, which has, until now, remained unexplored in tasks relying on incomplete training data.