Search Results for author:
Found 8 papers, 7 papers with code
A Structured Dictionary Perspective on Implicit Neural Representations
Leveraging results from harmonic analysis and deep learning theory, we show that most INR families are analogous to structured signal dictionaries whose atoms are integer harmonics of the set of initial mapping frequencies.
PRIME: A few primitives can boost robustness to common corruptions
Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data.
Ranked #28 on
Domain Generalization
on ImageNet-C
What can linearized neural networks actually say about generalization?
For certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization, but for the networks used in practice, the empirical NTK only provides a rough first-order approximation.
On the choice of graph neural network architectures
Seminal works on graph neural networks have primarily targeted semi-supervised node classification problems with few observed labels and high-dimensional signals.
Catastrophic overfitting can be induced with discriminative non-robust features
Through extensive experiments we analyze this novel phenomenon and discover that the presence of these easy features induces a learning shortcut that leads to CO. Our findings provide new insights into the mechanisms of CO and improve our understanding of the dynamics of AT.
Sparse Sampling for Inverse Problems with Tensors
We consider the problem of designing sparse sampling strategies for multidomain signals, which can be represented using tensors that admit a known multilinear decomposition.
Information Theory Signal Processing Information Theory
Sampling and Reconstruction of Signals on Product Graphs
In this paper, we consider the problem of subsampling and reconstruction of signals that reside on the vertices of a product graph, such as sensor network time series, genomic signals, or product ratings in a social network.
On the benefits of knowledge distillation for adversarial robustness
To that end, we present Adversarial Knowledge Distillation (AKD), a new framework to improve a model's robust performance, consisting on adversarially training a student on a mixture of the original labels and the teacher outputs.
