arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.11086cs.LGcs.AIcs.ITmath.ITstat.CO
收藏

利用Monte Carlo比特回退编码提高无损压缩率

Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding

University of Toronto(多伦多大学);Vector Institute(向量研究所);Facebook AI Research(脸书人工智能研究院);University College London(伦敦大学学院);University of Oxford(牛津大学)

Yangjun Ruan, Karen Ullrich, Daniel Severo, James Townsend, Ashish Khisti, Arnaud Doucet, Alireza Makhzani, Chris J. Maddison

摘要:

潜变量模型已成功地应用于无损压缩的比特回退编码算法。然而,比特返回遭受比特率的增加等于近似后验和真实后验之间的KL发散。在本文中,我们将展示如何消除这一差距渐近派生比特回编码算法从更严格的变分界限。其关键思想是利用扩展的空间表示的蒙特卡罗估计的边际似然。天真地应用,我们的计划将需要更多的初始位比标准的位回编码器,但我们展示了如何大大减少这种额外的成本与耦合的潜在空间。当可以利用并行架构时,我们的编码器可以实现比比特回退更好的速率,而几乎没有额外的成本。我们证明了改进的无损压缩率在各种设置,特别是在分布或顺序数据压缩。

英文摘要:

Latent variable models have been successfully applied in lossless compression with the bits-back coding algorithm. However, bits-back suffers from an increase in the bitrate equal to the KL divergence between the approximate posterior and the true posterior. In this paper, we show how to remove this gap asymptotically by deriving bits-back coding algorithms from tighter variational bounds. The key idea is to exploit extended space representations of Monte Carlo estimators of the marginal likelihood. Naively applied, our schemes would require more initial bits than the standard bits-back coder, but we show how to drastically reduce this additional cost with couplings in the latent space. When parallel architectures can be exploited, our coders can achieve better rates than bits-back with little additional cost. We demonstrate improved lossless compression rates in a variety of settings, especially in out-of-distribution or sequential data compression.

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。

↑