Papers › Neural Implicit Manifold Learning for Topology-Aware Density Estimation

Neural Implicit Manifold Learning for Topology-Aware Density Estimation

22 Jun 2022arXiv:2206.11267archive 2025-07-28

Brendan Leigh Ross, Gabriel Loaiza-Ganem, Anthony L. Caterini, Jesse C. Cresswell

Natural data observed in ℝⁿ is often constrained to an m-dimensional manifold ℳ, where m < n. This work focuses on the task of building theoretically principled generative models for such data. Current generative models learn ℳ by mapping an m-dimensional latent variable through a neural network f_θ: ℝᵐ →ℝⁿ. These procedures, which we call pushforward models, incur a straightforward limitation: manifolds cannot in general be represented with a single parameterization, meaning that attempts to do so will incur either computational instability or the inability to learn probability densities within the manifold. To remedy this problem, we propose to model ℳ as a neural implicit manifold: the set of zeros of a neural network. We then learn the probability density within ℳ with a constrained energy-based model, which employs a constrained variant of Langevin dynamics to train and sample from the learned manifold. In experiments on synthetic and natural data, we show that our model can learn manifold-supported distributions with complex topologies more accurately than pushforward models.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections