paper-with-me

홈 › Papers

Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport

2023-05-24 · NeurIPS 2023 11 · Jaemoo Choi, Jaewoong Choi, Myungjoo Kang

Optimal Transport (OT) problem investigates a transport map that bridges two distributions while minimizing a given cost function. In this regard, OT between tractable prior distribution and data has been utilized for generative modeling tasks. However, OT-based methods are susceptible to outliers and face optimization challenges during training. In this paper, we propose a novel generative model based on the semi-dual formulation of Unbalanced Optimal Transport (UOT). Unlike OT, UOT relaxes the hard constraint on distribution matching. This approach provides better robustness against outliers, stability during training, and faster convergence. We validate these properties empirically through experiments. Moreover, we study the theoretical upper-bound of divergence between distributions in UOT. Our model outperforms existing OT-based generative models, achieving FID scores of 2.97 on CIFAR-10 and 6.36 on CelebA-HQ-256. The code is available at \url{https://github.com/Jae-Moo/UOTM}.

📄 PDF Abstract BibTeX arXiv:2305.14777

Code (1)

Jae-Moo/UOTM 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Conditional Unbalanced Optimal Transport Maps: An Outlier-Robust Framework for Conditional Generative Modeling

2026-03-07 · Jiwoo Yoon, Kyumin Choi, Jaewoong Choi arxiv

Conditional Optimal Transport (COT) problem aims to find a transport map between conditional source and target distributions while minimizing the transport cost. Recently, these transport maps have been utilized in condi…

Primal-Dual Wasserstein GAN

2018-05-24 · Mevlana Gemici, Zeynep Akata, Max Welling

We introduce Primal-Dual Wasserstein GAN, a new learning algorithm for building latent variable models of the data distribution based on the primal and the dual formulations of the optimal transport (OT) problem. We util…

Decoder

A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers

2025-02-03 · Roman Tarasov, Petr Mokrov, Milena Gazdieva, Evgeny Burnaev 외

Neural network-based optimal transport (OT) is a recent and fruitful direction in the generative modeling community. It finds its applications in various fields such as domain translation, image super-resolution, computa…

Image Super-ResolutionSuper-Resolution

Near-optimal estimation of smooth transport maps with kernel sums-of-squares

2021-12-03 · Boris Muzellec, Adrien Vacher, Francis Bach, François-Xavier Vialard 외

It was recently shown that under smoothness conditions, the squared Wasserstein distance between two distributions could be efficiently computed with appealing statistical error upper bounds. However, rather than the dis…

A General Framework for Joint Multi-State Models

2025-10-08 · Félix Laplante, Christophe Ambroise arxiv

Conventional joint modeling approaches generally characterize the relationship between longitudinal biomarkers and discrete event occurrences within terminal, recurring or competing risk settings, thereby offering a limi…