paper-with-me

Papers

Learning disconnected manifolds: a no GAN's land

2020-01-01 · ICML 2020 1 · Ugo Tanielian, Thibaut Issenhuth, Elvis Dohmatob, Jeremie Mary

Typical architectures of Generative Adversarial Networks make use of a unimodal latent/input distribution transformed by a continuous generator. Consequently, the modeled distribution always has connected support which is cumbersome when learning a disconnected set of manifolds. We formalize this problem by establishing a "no free lunch" theorem for the disconnected manifold learning stating an upper-bound on the precision of the targeted distribution. This is done by building on the necessary existence of a low-quality region where the generator continuously samples data between two disconnected modes. Finally, we derive a rejection sampling method based on the norm of generator’s Jacobian and show its efficiency on several generators including BigGAN.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning disconnected manifolds: a no GANs land

2020-06-08 · Ugo Tanielian, Thibaut Issenhuth, Elvis Dohmatob, Jeremie Mary

Typical architectures of Generative AdversarialNetworks make use of a unimodal latent distribution transformed by a continuous generator. Consequently, the modeled distribution always has connected support which is cumbe…

Learning Disconnected Manifolds: Avoiding The No Gan's Land by Latent Rejection

2021-01-01 · Thibaut Issenhuth, Ugo Tanielian, David Picard, Jeremie Mary

Standard formulations of GANs, where a continuous function deforms a connected latent space, have been shown to be misspecified when fitting disconnected manifolds. In particular, when covering different classes of image…

DiRe-RAPIDS: Topology-faithful dimensionality reduction at scale

2026-04-28 · Alexander Kolpakov, Igor Rivin arxiv

Dimensionality reduction methods such as UMAP and t-SNE are central tools for visualising high-dimensional data, but their local-neighborhood objectives can preserve sampling noise while distorting global topology. We sh…

Dimensionality Reduction

Disconnected Manifold Learning for Generative Adversarial Networks

2018-06-03 · NeurIPS 2018 12 · Mahyar Khayatkhoei, Ahmed Elgammal, Maneesh Singh

Natural images may lie on a union of disjoint manifolds rather than one globally connected manifold, and this can cause several difficulties for the training of common Generative Adversarial Networks (GANs). In this work…

Flexible Multi-Generator Model with Fused Spatiotemporal Graph for Trajectory Prediction

2023-11-06 · Peiyuan Zhu, Fengxia Han, Hao Deng

Trajectory prediction plays a vital role in automotive radar systems, facilitating precise tracking and decision-making in autonomous driving. Generative adversarial networks with the ability to learn a distribution over…

Autonomous DrivingDecision MakingTrajectory Prediction