论文标题
神经网络是否最佳地压缩歧管？
Do Neural Networks Compress Manifolds Optimally?
论文作者
论文摘要
基于人工神经网络（基于ANN）的损耗压缩机最近在多个来源获得了惊人的结果。它们的成功可能归因于在高维环境空间中识别低维歧管的结构的能力。实际上，先前的工作表明，基于ANN的压缩机可以实现某些此类来源的最佳熵距离曲线。相比之下，我们确定了具有圆形结构的两个低维歧管的最佳熵差异权，并表明基于最新的ANN压缩机无法最佳地压缩它们。
Artificial Neural-Network-based (ANN-based) lossy compressors have recently obtained striking results on several sources. Their success may be ascribed to an ability to identify the structure of low-dimensional manifolds in high-dimensional ambient spaces. Indeed, prior work has shown that ANN-based compressors can achieve the optimal entropy-distortion curve for some such sources. In contrast, we determine the optimal entropy-distortion tradeoffs for two low-dimensional manifolds with circular structure and show that state-of-the-art ANN-based compressors fail to optimally compress them.
