论文标题
积极的噪音
Positive-incentive Noise
论文作者
论文摘要
通常，噪声被视为不同领域的严重问题，例如工程，学习系统。但是，本文旨在调查传统命题是否始终存在。它始于任务熵的定义，该定义从信息熵延伸，并测量任务的复杂性。引入任务熵后，噪声可以分为两种，即正质噪声（pi-noise或$π$ -NOISE）和纯噪声，并根据噪声是否可以降低任务的复杂性。有趣的是，如理论和经验上所示，即使简单的随机噪声也可以是简化任务的$π$ - noise。 $π$ -Noise为某些模型提供了新的解释，并为某些领域（例如多任务学习，对抗性培训等）提供了一个新的原则。此外，它提醒我们重新考虑对噪音的调查。
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.
