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 2408.00549cs.LGcs.AIeess.SPstat.ML
收藏

通过最大核熵学习嵌入分布

Learning to Embed Distributions via Maximum Kernel Entropy

Dipartimento di Matematica, Università degli Studi di Genova(热那亚大学数学系);Technion Israel Institute of Technology(以色列理工学院);Allen Institute for Neural Dynamics(艾伦神经动力学研究所)

Oleksii Kachaiev, Stefano Recanatesi

AI总结:

针对分布回归任务中核函数选择难题,本文提出基于概率测度嵌入空间熵最大化的无监督数据依赖型分布核学习方法,理论验证其嵌入空间几何结构适用于下游判别任务,且在多模态下表现良好。

摘要:

经验数据通常可视为来自一组概率分布的样本。核方法已成为对这些分布进行分类学习的自然方法。尽管已提出多种分布间的核函数,但将核方法应用于分布回归任务仍具挑战性,主要因选择合适核函数并非易事。令人惊讶的是,学习数据依赖型分布核的问题尚未得到足够关注。本文基于概率测度嵌入空间中的熵最大化原理,提出一种无监督学习数据依赖型分布核的新目标函数。我们研究了该目标函数诱导的潜在嵌入空间的理论性质,证明其几何结构非常适合解决下游判别任务。最后,我们展示了所学习核函数在不同模态下的性能。

英文摘要:

Empirical data can often be considered as samples from a set of probability distributions. Kernel methods have emerged as a natural approach for learning to classify these distributions. Although numerous kernels between distributions have been proposed, applying kernel methods to distribution regression tasks remains challenging, primarily because selecting a suitable kernel is not straightforward. Surprisingly, the question of learning a data-dependent distribution kernel has received little attention. In this paper, we propose a novel objective for the unsupervised learning of data-dependent distribution kernel, based on the principle of entropy maximization in the space of probability measure embeddings. We examine the theoretical properties of the latent embedding space induced by our objective, demonstrating that its geometric structure is well-suited for solving downstream discriminative tasks. Finally, we demonstrate the performance of the learned kernel across different modalities.

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。

↑