关于无监督表示学习的最小变化
On minimal variations for unsupervised representation learning
AI总结：
本文提出将最小变化作为无监督表示学习的统一指导原则，以解释流形学习、扩散映射和自监督学习方法的共同假设，并为改进自监督算法提供实践依据。
摘要：
无监督表示学习旨在高效描述原始数据，以解决各种下游任务。人们已采用多种技术来处理该问题，例如流形学习、扩散映射，以及近年来的自监督学习。可以说，这些技术都基于一个潜在假设：与未来下游任务相关的目标函数，在输入空间中人口稠密区域内具有较低变化。揭示最小变化作为无监督表示学习背后的指导原则，为自监督学习算法形成更好的实践准则铺平了道路。
英文摘要：
Unsupervised representation learning aims at describing raw data efficiently to solve various downstream tasks. It has been approached with many techniques, such as manifold learning, diffusion maps, or more recently self-supervised learning. Those techniques are arguably all based on the underlying assumption that target functions, associated with future downstream tasks, have low variations in densely populated regions of the input space. Unveiling minimal variations as a guiding principle behind unsupervised representation learning paves the way to better practical guidelines for self-supervised learning algorithms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
