A Coding-Theoretic Analysis of Hyperspherical Prototypical Learning Geometry
Hyperspherical Prototypical Learning (HPL) is a supervised approach to representation learning that designs class prototypes on the unit hypersphere. The prototypes bias the representations to class separation in a scale invariant and known geometry. Previous approaches to HPL have either of the following shortcomings: (i) they follow an unprincipled optimisation procedure; or (ii) they are theoretically sound, but are constrained to only one possible latent dimension. In this paper, we address both shortcomings. To address (i), we present a principled optimisation procedure whose solution we show is optimal. To address (ii), we construct well-separated prototypes in a wide range of dimensions using linear block codes. Additionally, we give a full characterisation of the optimal prototype placement in terms of achievable and converse bounds, showing that our proposed methods are near-optimal.
Code (1)
Tasks
Representation LearningSimilar Papers 제목 키워드 기반
Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres
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 …
HYPO: Hyperspherical Out-of-Distribution Generalization
Out-of-distribution (OOD) generalization is critical for machine learning models deployed in the real world. However, achieving this can be fundamentally challenging, as it requires the ability to learn invariant feature…
Out-of-Distribution GeneralizationSelf-Supervised Representation Learning via Hyperspherical Density Shaping
Modern self-supervised representation learning methods often relies on empirical heuristics that are not theoretically grounded. In this study we propose HyDeS, a theoretically grounded method based on multi-view mutual …
Self-Supervised LearningRepresentation LearningHyperspherical Latents Improve Continuous-Token Autoregressive Generation
Autoregressive (AR) models are promising for image generation, yet continuous-token AR variants often trail latent diffusion and masked-generation models. The core issue is heterogeneous variance in VAE latents, which is…
Image GenerationGeometry-Preserving Aggregation for Mixture-of-Experts Embedding Models
Mixture-of-Experts (MoE) embedding models combine expert outputs using weighted linear summation, implicitly assuming a linear subspace structure in the embedding space. This assumption is shown to be inconsistent with t…
Semantic Similarity