To this end, we first establish a new class of GNNs that can solve a strictly wider variety of problems than existing GNNs. Then, we bridge the gap between GNN theory and the theory of distributed local algorithms.

We now report the implementation details for the reproducibility of our method.

Thus, they do not effectively capture implicit correspondences between articulated shapes or regularize jittery temporal deformations.

We consider the problem of online forecasting of sequences of lengthn with total-variation at mostCn using observations contaminated by independentσsubgaussian noise. We design anO(nlogn)-time algorithm that achieves a cu-mulativesquare error of O(n1/3C2/3n σ4/3+C2n)with high probability.

We introduce chefs' random tables(CRTs), a new class of non-trigonometric random features (RFs) toapproximate Gaussian andsoftmax-kernels.

The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn?

However, prior attempts to include equivariances in CNPs do not scale effectively beyond two input dimensions.