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 2407.18436cs.LGcs.DS
收藏

组合字典学习与推断模型

A Model for Combinatorial Dictionary Learning and Inference

Toyota Technological Institute at Chicago(芝加哥丰田理工学院)

Avrim Blum, Kavya Ravichandran

AI总结:

受图像遮挡启发提出组合字典学习与推断模型,定义“良结构性”保证潜在成分可学习,并解决实例成分溯源及对抗鲁棒性问题,证明无假设下计算不可行。

摘要:

我们通常希望将复杂且结构化的数据分解为能够解释该数据的简单成分。该问题的线性版本作为字典学习和因子分析已被广泛研究。在本工作中,受场景中物体相互遮挡以形成图像的方式启发,我们提出了一个组合模型来研究这一问题。首先,我们识别出一组低维成分的一种性质,称之为“良结构性”,它确保集合中没有两个成分过于相似。我们展示了良结构性如何足以用于学习构成一组样本实例的潜在成分集合。随后我们考虑以下问题:给定一组成分以及由其中某个未知子集生成的实例,识别实例的哪些部分源自哪些成分。我们考虑了两种变体:(1)确定解释该实例所需的最少成分数量;(2)尽可能多地确定各位置的正确解释。对于后一目标,在仅对成分施加稍强假设的情况下,我们还设计了一种对对抗性破坏具有鲁棒性的版本。最后,我们证明在没有任何假设的情况下,该学习问题在计算上是不可行的。

英文摘要:

We are often interested in decomposing complex, structured data into simple components that explain the data. The linear version of this problem is well-studied as dictionary learning and factor analysis. In this work, we propose a combinatorial model in which to study this question, motivated by the way objects occlude each other in a scene to form an image. First, we identify a property we call "well-structuredness" of a set of low-dimensional components which ensures that no two components in the set are too similar. We show how well-structuredness is sufficient for learning the set of latent components comprising a set of sample instances. We then consider the problem: given a set of components and an instance generated from some unknown subset of them, identify which parts of the instance arise from which components. We consider two variants: (1) determine the minimal number of components required to explain the instance; (2) determine the correct explanation for as many locations as possible. For the latter goal, we also devise a version that is robust to adversarial corruptions, with just a slightly stronger assumption on the components. Finally, we show that the learning problem is computationally infeasible in the absence of any assumptions.

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。

↑