A systematic approach maps any-dimensional invariant functions to a unique function on an infinite-dimensional limit space admitting a topology with compact sets where universality holds, with examples of non-universal architectures and fixes.
Invariant kernels: Rank stabilization and generalization across dimensions
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Symmetry arises often when learning from high dimensional data. For example, data sets consisting of point clouds, graphs, and unordered sets appear routinely in contemporary applications, and exhibit rich underlying symmetries. Understanding the benefits of symmetry on the statistical and numerical efficiency of learning algorithms is an active area of research. In this work, we show that symmetry has a pronounced impact on the rank of kernel matrices. Specifically, we compute the rank of a polynomial kernel of fixed degree that is invariant under various groups acting independently on its two arguments. In concrete circumstances, including the three aforementioned examples, symmetry dramatically decreases the rank making it independent of the data dimension. In such settings, we show that a simple regression procedure is minimax optimal for estimating an invariant polynomial from finitely many samples drawn across different dimensions. We complete the paper with numerical experiments that illustrate our findings.
years
2026 3representative citing papers
Random sampling maps (with-replacement, binning, species) induce metrics that give uniform any-dimensional generalization and sketching rates for continuous functions on sequences, graphs and tensors.
Partial random data augmentation matches full group augmentation's minimax rates up to vanishing approximation error for classical learning problems, but exact invariance requires the full group for expressive hypotheses.
citing papers explorer
-
Any-Dimensional Invariant Universality
A systematic approach maps any-dimensional invariant functions to a unique function on an infinite-dimensional limit space admitting a topology with compact sets where universality holds, with examples of non-universal architectures and fixes.
-
Any-Dimensional Learning by Sampling
Random sampling maps (with-replacement, binning, species) induce metrics that give uniform any-dimensional generalization and sketching rates for continuous functions on sequences, graphs and tensors.
-
Data Augmentation: A Fourier Analysis Perspective
Partial random data augmentation matches full group augmentation's minimax rates up to vanishing approximation error for classical learning problems, but exact invariance requires the full group for expressive hypotheses.