We study the generalization properties of batched predictors, i.e., mode...
The Abstraction and Reasoning Corpus (ARC) (Chollet, 2019) and its most
...
Generative flow networks (GFlowNets) are a family of algorithms that lea...
How much explicit guidance is necessary for conditional diffusion? We
co...
Deep generative models have emerged as a popular machine learning-based
...
Generalization analyses of deep learning typically assume that the train...
Integrating functions on discrete domains into neural networks is key to...
We approach the graph generation problem from a spectral perspective by ...
State-of-the-art approaches to reasoning and question answering over
kno...
Can we use machine learning to compress graph data? The absence of order...
This work explores the hypothesis that the complexity of the function a ...
Attention-based architectures have become ubiquitous in machine learning...
Attention layers are widely used in natural language processing (NLP) an...
Message-passing has proved to be an effective way to design graph neural...
Combinatorial optimization problems are notoriously challenging for neur...
A hallmark of graph neural networks is their ability to distinguish the
...
Recent trends of incorporating attention mechanisms in vision have led
r...
This paper studies the capacity limits of graph neural networks (GNN). R...
This paper focuses on the discrimination capacity of aggregation functio...
Deep convolutional neural networks have been shown to be able to fit a
l...
We consider the problem of path inference: given a path prefix, i.e., a
...
Spectral clustering refers to a family of unsupervised learning algorith...
How can we reduce the size of a graph without significantly altering its...
How does coarsening affect the spectrum of a general graph? We provide
c...
Spectral clustering is a widely studied problem, yet its complexity is
p...
How many samples are sufficient to guarantee that the eigenvectors and
e...
The goal of this paper is to improve learning for multivariate processes...
An emerging way of tackling the dimensionality issues arising in the mod...
Graph-based methods for signal processing have shown promise for the ana...
One of the cornerstones of the field of signal processing on graphs are ...
This letter extends the concept of graph-frequency to graph signals that...