Graph neural networks (GNNs) are commonly described as being permutation...
Self-supervised learning converts raw perceptual data such as images to ...
Numerous recent works have analyzed the expressive power of message-pass...
Convolutional neural networks and their ilk have been very successful fo...
Any representation of data involves arbitrary investigator choices. Beca...
We introduce a sketch-and-solve approach to speed up the Peng-Wei
semide...
Spectral methods provide consistent estimators for community detection i...
Deep neural networks (DNNs) are capable of perfectly fitting the trainin...
The shuffled linear regression problem aims to recover linear relationsh...
In equivariant machine learning the idea is to restrict the learning to ...
Graph Neural Networks (GNNs) are powerful deep learning methods for
Non-...
Single-cell RNA-seq data allow the quantification of cell type differenc...
Units equivariance is the exact symmetry that follows from the requireme...
Graph neural networks are designed to learn functions on graphs. Typical...
Physical systems obey strict symmetry principles. We expect that machine...
There has been enormous progress in the last few years in designing
conc...
There are many uses for linear fitting; the context here is interpolatio...
Overparameterization in deep learning is powerful: Very large models fit...
The ability to detect and count certain substructures in graphs is impor...
Comparing and aligning large datasets is a pervasive problem occurring a...
Comparing and aligning large datasets is a pervasive problem occurring a...
This note explores the applicability of unsupervised machine learning
te...
Graph neural networks (GNNs) have achieved lots of success on
graph-stru...
Inspired by the word game Ghost, we propose a new protocol for bipartisa...
Given labeled points in a high-dimensional vector space, we seek a
low-d...
Gerrymandering is a long-standing issue within the U.S. political system...
It has been experimentally established that deep neural networks can be ...
Efficient algorithms for k-means clustering frequently converge to
subop...
The network alignment problem asks for the best correspondence between t...
Many inverse problems are formulated as optimization problems over certa...
The Gromov-Hausdorff distance provides a metric on the set of isometry
c...
We introduce a model-free relax-and-round algorithm for k-means clusteri...
Recently, Awasthi et al. introduced an SDP relaxation of the k-means
pro...