arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15319cs.LGstat.ML
收藏

用于数据压缩的贝叶斯注意力网络

Bayesian Attention Networks for Data Compression

Volkswagen Group of America Innovation Center California(大众汽车美国创新中心加州);BayzAI

Michael Tetelman

摘要:

从第一性原理出发,推导了基于贝叶斯注意网络的无损数据压缩算法。贝叶斯注意力网络是通过将每个训练样本损失的注意力因子作为来自训练样本和预测样本的两个样本输入的函数来定义的。通过使用锐化詹森不等式,我们表明,注意力因子是完全由两个样本的相关函数w.r.t.模型的权重。由于注意力因素,预测样本的解决方案主要由与预测样本相关的几个训练样本定义。找到每个预测样本的特定解决方案将训练和预测耦合在一起。为了使该方法实用,我们引入了一个潜在空间,将每个预测样本映射到潜在空间,并学习所有可能的解决方案作为潜在空间的函数,同时学习注意力作为潜在空间和训练样本的函数。潜在空间扮演上下文表示的角色,其中预测样本定义上下文和用于预测的学习上下文相关解决方案。

英文摘要:

The lossless data compression algorithm based on Bayesian Attention Networks is derived from first principles. Bayesian Attention Networks are defined by introducing an attention factor per a training sample loss as a function of two sample inputs, from training sample and prediction sample. By using a sharpened Jensen's inequality we show that the attention factor is completely defined by a correlation function of the two samples w.r.t. the model weights. Due to the attention factor the solution for a prediction sample is mostly defined by a few training samples that are correlated with the prediction sample. Finding a specific solution per prediction sample couples together the training and the prediction. To make the approach practical we introduce a latent space to map each prediction sample to a latent space and learn all possible solutions as a function of the latent space along with learning attention as a function of the latent space and a training sample. The latent space plays a role of the context representation with a prediction sample defining a context and a learned context dependent solution used for the prediction.

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。

↑