Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
This work addresses the problem of improving nonparametric generative modeling for researchers and practitioners in machine learning, offering a novel conditional extension and enhanced image modeling, though it is incremental in building upon existing SWF methods.
The paper tackled the suboptimal generative quality and lack of conditional modeling in Sliced-Wasserstein Flow (SWF) by proposing Conditional Sliced-Wasserstein Flow (CSWF) and incorporating image-specific inductive biases, achieving generative performance comparable to deep parametric models on conditional and unconditional tasks.
Sliced-Wasserstein Flow (SWF) is a promising approach to nonparametric generative modeling but has not been widely adopted due to its suboptimal generative quality and lack of conditional modeling capabilities. In this work, we make two major contributions to bridging this gap. First, based on a pleasant observation that (under certain conditions) the SWF of joint distributions coincides with those of conditional distributions, we propose Conditional Sliced-Wasserstein Flow (CSWF), a simple yet effective extension of SWF that enables nonparametric conditional modeling. Second, we introduce appropriate inductive biases of images into SWF with two techniques inspired by local connectivity and multiscale representation in vision research, which greatly improve the efficiency and quality of modeling images. With all the improvements, we achieve generative performance comparable with many deep parametric generative models on both conditional and unconditional tasks in a purely nonparametric fashion, demonstrating its great potential.