paper-with-me

홈 › Papers

Staying on the Manifold: Geometry-Aware Noise Injection

2025-09-24 · Albert Kjøller Jacobsen, Johanna Marie Gegenfurtner, Georgios Arvanitidis arxiv

It has been shown that perturbing the input during training implicitly regularises the gradient of the learnt function, leading to smoother models and enhancing generalisation. However, previous research mostly considered the addition of ambient noise in the input space, without considering the underlying structure of the data. In this work, we propose several strategies of adding geometry-aware input noise that accounts for the lower dimensional manifold the input space inhabits. We start by projecting ambient Gaussian noise onto the tangent space of the manifold. In a second step, the noise sample is mapped on the manifold via the associated geodesic curve. We also consider Brownian motion noise, which moves in random steps along the manifold. We show that geometry-aware noise leads to improved generalisation and robustness to hyperparameter selection on highly curved manifolds, while performing at least as well as training without noise on simpler manifolds. Our proposed framework extends to data manifolds approximated by generative models and we observe similar trends on the MNIST digits dataset.

📄 PDF Abstract BibTeX arXiv:2509.20201

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry

2022-05-31 · Miguel González-Duque, Rasmus Berg Palm, Søren Hauberg, Sebastian Risi

Deep generative models can automatically create content of diverse types. However, there are no guarantees that such content will satisfy the criteria necessary to present it to end-users and be functional, e.g. the gene…

JGRA: Jacobian Geometry Robustness Assessment in NISQ Noise-Aware Quantum Neural Networks

2026-06-08 · Gianluca Scanu, Luca Barletta, Stefano Rini arxiv

The NISQ era places stringent constraints on quantum computation, where noise and decoherence fundamentally limit performance. In classical deep learning, model robustness and resilience to perturbations are well studied…

Quantum Machine Learning

Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres

2025-06-12 · Muskan Dosi, Chiranjeev Chiranjeev, Kartik Thakral, Mayank Vatsa 외

Do contemporary diffusion models preserve the class geometry of hyperspherical data? Standard diffusion models rely on isotropic Gaussian noise in the forward process, inherently favoring Euclidean spaces. However, many …

GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds

2025-05-05 · Aoran Chen, Yang Feng

Multi-Task Learning (MTL) seeks to boost statistical power and learning efficiency by discovering structure shared across related tasks. State-of-the-art MTL representation methods, however, usually treat the latent repr…

Activity RecognitionMulti-Task LearningRepresentation Learning

On Noise Injection in Generative Adversarial Networks

2020-06-10 · Ruili Feng, Deli Zhao, ZhengJun Zha

Noise injection has been proved to be one of the key technique advances in generating high-fidelity images. Despite its successful usage in GANs, the mechanism of its validity is still unclear. In this paper, we propose …

Image Generation