深度条件测度量化
Deep Conditional Measure Quantization
AI总结:
本文提出DCMQ方法,结合Huber能量核与深度神经网络,用于条件概率测度的量化,在多个示例上取得良好效果。
摘要:
概率测度的量化是指用一组有限的狄拉克质量来近似输入分布(在某个概率测度度量空间中)的过程。已有多种方法可实现此目标,但对条件分布的量化情形研究较少。我们提出了一种名为DCMQ的方法,该方法结合了基于Huber能量核的方法与深度神经网络架构。该方法在多个示例上进行了测试,并取得了有前景的结果。
英文摘要:
Quantization of a probability measure means representing it with a finite set of Dirac masses that approximates the input distribution well enough (in some metric space of probability measures). Various methods exists to do so, but the situation of quantizing a conditional law has been less explored. We propose a method, called DCMQ, involving a Huber-energy kernel-based approach coupled with a deep neural network architecture. The method is tested on several examples and obtains promising results.
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。