paper-with-me

Papers

Riemannian generative decoder

2025-06-23 · Andreas Bjerregaard, Søren Hauberg, Anders Krogh

Riemannian representation learning typically relies on approximating densities on chosen manifolds. This involves optimizing difficult objectives, potentially harming models. To completely circumvent this issue, we introduce the Riemannian generative decoder which finds manifold-valued maximum likelihood latents with a Riemannian optimizer while training a decoder network. By discarding the encoder, we vastly simplify the manifold constraint compared to current approaches which often only handle few specific manifolds. We validate our approach on three case studies -- a synthetic branching diffusion process, human migrations inferred from mitochondrial DNA, and cells undergoing a cell division cycle -- each showing that learned representations respect the prescribed geometry and capture intrinsic non-Euclidean structure. Our method requires only a decoder, is compatible with existing architectures, and yields interpretable latent spaces aligned with data geometry.

📄 PDF Abstract BibTeX arXiv:2506.19133

Code (1)

yhsure/riemannian-generative-decoder 공식 구현 pytorch

Tasks

DecoderRepresentation Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Riemannian AmbientFlow: Towards Simultaneous Manifold Learning and Generative Modeling from Corrupted Data

2026-01-26 · Willem Diepeveen, Oscar Leong arxiv

Modern generative modeling methods have demonstrated strong performance in learning complex data distributions from clean samples. In many scientific and imaging applications, however, clean samples are unavailable, and …

Counterfactual Explanations via Riemannian Latent Space Traversal

2024-11-04 · Paraskevas Pegios, Aasa Feragen, Andreas Abildtrup Hansen, Georgios Arvanitidis

The adoption of increasingly complex deep models has fueled an urgent need for insight into how these models make predictions. Counterfactual explanations form a powerful tool for providing actionable explanations to pra…

counterfactualCounterfactual ExplanationDecoder

PepCompass: Navigating peptide embedding spaces using Riemannian Geometry

2025-10-02 · Marcin Możejko, Adam Bielecki, Jurand Prądzyński, Marcin Traskowski 외 arxiv

Antimicrobial peptide discovery is challenged by the astronomical size of peptide space and the relative scarcity of active peptides. Generative models provide continuous latent "maps" of peptide space, but conventionall…

Uncertainty Estimation Using Riemannian Model~Dynamics for Offline Reinforcement Learning

2021-02-22 · Guy Tennenholtz, Shie Mannor

Model-based offline reinforcement learning approaches generally rely on bounds of model error. Estimating these bounds is usually achieved through uncertainty estimation methods. In this work, we combine parametric and n…

Autonomous Drivingcontinuous-controlContinuous ControlDecoder+4

Riemannian Score-Based Generative Modelling

2022-02-06 · Valentin De Bortoli, Emile Mathieu, Michael Hutchinson, James Thornton 외

Score-based generative models (SGMs) are a powerful class of generative models that exhibit remarkable empirical performance. Score-based generative modelling (SGM) consists of a ``noising'' stage, whereby a diffusion is…

Denoising