用于潜变量识别与笛卡尔积外推的加法解码器
Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation
AI总结:
本文提出加法解码器框架,在弱分布假设下证明其可识别潜变量块并实现笛卡尔积外推生成,模拟实验验证了加法性的关键作用。
摘要:
我们解决表征学习中的潜变量识别和“支撑集外”图像生成问题。我们表明,对于一类我们称为加法的解码器,这两者都是可能的;这类解码器让人想起用于以对象为中心的表征学习(OCRL)的解码器,并且非常适合可分解为特定对象图像之和的图像。我们给出了若干条件,在这些条件下,使用加法解码器精确求解重建问题,可保证识别出潜变量的各个块,至多存在排列和逐块可逆变换。这一保证仅依赖于对潜在因子分布的非常弱的假设;这些因子可能呈现统计依赖性,并且具有几乎任意形状的支撑集。我们的结果提供了一个可实现非线性独立成分分析(ICA)的新设定,并增进了我们对 OCRL 方法的理论理解。我们还从理论上表明,加法解码器能够通过以新颖方式重新组合观察到的变化因子来生成新颖图像,我们将这种能力称为笛卡尔积外推。我们在模拟数据上通过实验表明,加法性对于可识别性和外推都至关重要。
英文摘要:
We tackle the problems of latent variables identification and ``out-of-support'' image generation in representation learning. We show that both are possible for a class of decoders that we call additive, which are reminiscent of decoders used for object-centric representation learning (OCRL) and well suited for images that can be decomposed as a sum of object-specific images. We provide conditions under which exactly solving the reconstruction problem using an additive decoder is guaranteed to identify the blocks of latent variables up to permutation and block-wise invertible transformations. This guarantee relies only on very weak assumptions about the distribution of the latent factors, which might present statistical dependencies and have an almost arbitrarily shaped support. Our result provides a new setting where nonlinear independent component analysis (ICA) is possible and adds to our theoretical understanding of OCRL methods. We also show theoretically that additive decoders can generate novel images by recombining observed factors of variations in novel ways, an ability we refer to as Cartesian-product extrapolation. We show empirically that additivity is crucial for both identifiability and extrapolation on simulated data.
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。