arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.00372cs.LGcs.NAmath.NA
收藏

张量场因子化嵌入的样本高效学习

Sample Efficient Learning of Factored Embeddings of Tensor Fields

University of Texas at Austin(德克萨斯大学奥斯汀分校)

Taemin Heo, Chandrajit Bajaj

AI总结:

针对大规模张量场数据直接访问成本高的问题,提出样本高效的张量场因子化嵌入方法,通过子采样构建因子矩阵实现最优秩r草图Tucker分解,用带共轭先验的Dirichlet分布的自适应随机Thompson采样学习采样策略,提升信息处理效率且精度可定制。

摘要:

二阶及更高阶的数据张量如今已被常规生成,这类数据集合规模日益庞大且仍在增长。许多科学与医学数据张量属于张量场(例如图像、视频、地理数据),其空间邻域包含重要信息。直接访问这类大型数据张量集合以获取信息的成本已变得越来越高昂。我们学习具有分解表示的近似满秩且紧凑的张量草图,可提供张量场的紧凑空间、时间与谱嵌入。由于所有信息查询与后处理都在潜在生成空间中的这些紧凑因子化草图上执行,如今能以可定制的精度更高效地完成对原始张量场的此类操作。我们通过对张量切片进行样本高效的子采样构建紧凑因子矩阵,实现任意阶数据张量的最优秩r草图Tucker分解。我们的样本高效策略通过采用带共轭先验的Dirichlet分布的自适应随机Thompson采样学习得到。

英文摘要:

Data tensors of orders 2 and greater are now routinely being generated. These data collections are increasingly huge and growing. Many scientific and medical data tensors are tensor fields (e.g., images, videos, geographic data) in which the spatial neighborhood contains important information. Directly accessing such large data tensor collections for information has become increasingly prohibitive. We learn approximate full-rank and compact tensor sketches with decompositive representations providing compact space, time and spectral embeddings of tensor fields. All information querying and post-processing on the original tensor field can now be achieved more efficiently and with customizable accuracy as they are performed on these compact factored sketches in latent generative space. We produce optimal rank-r sketchy Tucker decomposition of arbitrary order data tensors by building compact factor matrices from a sample-efficient sub-sampling of tensor slices. Our sample efficient policy is learned via an adaptable stochastic Thompson sampling using Dirichlet distributions with conjugate priors.

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。

↑