Group-invariant probability distributions appear in many data-generative models in machine learning, such as graphs, point clouds, and images. In practice, one often needs to estimate divergences between such distributions. In this work, we study how the inherent invariances, with respect to any smooth action of a Lie group on a manifold, improve sample complexity when estimating the Wasserstein distance, the Sobolev Integral Probability Metrics (Sobolev IPMs), the Maximum Mean Discrepancy (MMD), and also the complexity of the density estimation problem (in the $L^2$ and $L^\infty$ distance). Our results indicate a two-fold gain: (1) reducing the sample complexity by a multiplicative factor corresponding to the group size (for finite groups) or the normalized volume of the quotient space (for groups of positive dimension); (2) improving the exponent in the convergence rate (for groups of positive dimension). These results are completely new for groups of positive dimension and extend recent bounds for finite group actions.
In practice, encoding invariances into models helps sample complexity. In this work, we tighten and generalize theoretical results on how invariances improve sample complexity. In particular, we provide minimax optimal rates for kernel ridge regression on any manifold, with a target function that is invariant to an arbitrary group action on the manifold. Our results hold for (almost) any group action, even groups of positive dimension. For a finite group, the gain increases the "effective" number of samples by the group size. For groups of positive dimension, the gain is observed by a reduction in the manifold's dimension, in addition to a factor proportional to the volume of the quotient space. Our proof takes the viewpoint of differential geometry, in contrast to the more common strategy of using invariant polynomials. Hence, this new geometric viewpoint on learning with invariances may be of independent interest.
While massage passing based Graph Neural Networks (GNNs) have become increasingly popular architectures for learning with graphs, recent works have revealed important shortcomings in their expressive power. In response, several higher-order GNNs have been proposed, which substantially increase the expressive power, but at a large computational cost. Motivated by this gap, we introduce and analyze a new recursive pooling technique of local neighborhoods that allows different tradeoffs of computational cost and expressive power. First, we show that this model can count subgraphs of size $k$, and thereby overcomes a known limitation of low-order GNNs. Second, we prove that, in several cases, the proposed algorithm can greatly reduce computational complexity compared to the existing higher-order $k$-GNN and Local Relational Pooling (LRP) networks. We also provide a (near) matching information-theoretic lower bound for graph representations that can provably count subgraphs, and discuss time complexity lower bounds as well.