Positive-incentive Noise
This work offers a new perspective on noise that could impact fields like multi-task learning and adversarial training, though it appears incremental in rethinking existing concepts.
The paper challenges the conventional view of noise as detrimental by introducing task entropy to classify noise as either positive-incentive (Pi-noise) or pure noise, showing theoretically and empirically that even random noise can simplify tasks.
Noise is conventionally viewed as a severe problem in diverse fields, e.g., engineering, learning systems. However, this paper aims to investigate whether the conventional proposition always holds. It begins with the definition of task entropy, which extends from the information entropy and measures the complexity of the task. After introducing the task entropy, the noise can be classified into two kinds, Positive-incentive noise (Pi-noise or $π$-noise) and pure noise, according to whether the noise can reduce the complexity of the task. Interestingly, as shown theoretically and empirically, even the simple random noise can be the $π$-noise that simplifies the task. $π$-noise offers new explanations for some models and provides a new principle for some fields, such as multi-task learning, adversarial training, etc. Moreover, it reminds us to rethink the investigation of noises.