A General Theory of Equivariant CNNs on Homogeneous Spaces

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Dimension is a fundamental property of objects and the space in which they are embedded. Yet ideal notions of dimension, as in Euclidean spaces, do not always translate to physical spaces, which can be constrained by boundaries and distorted by inhomogenei ...

Even the largest neural networks make errors, and once-correct predictions can become invalid as the world changes. Model editors make local updates to the behavior of base (pre-trained) models to inject updated knowledge or correct undesirable behaviors. ...

Recently, it has been shown that, in spite of the significant performance of deep neural networks in different fields, those are vulnerable to adversarial examples. In this paper, we propose a gradient-based adversarial attack against transformer-based tex ...

In this thesis, we study the stochastic heat equation (SHE) on bounded domains and on the whole Euclidean space

\R^d.

We confirm the intuition that as the bounded domain increases to the whole space, both solutions become arbitrarily close to one another ...

The field of computational topology has developed many powerful tools to describe the shape of data, offering an alternative point of view from classical statistics. This results in a variety of complex structures that are not always directly amenable for ...

In this paper we present a new construction of a discrete Fourier uniqueness set in Euclidean space. ...

Supervised and unsupervised kernel-based algorithms widely used in the physical sciences depend upon the notion of similarity. Their reliance on pre-defined distance metrics-e.g. the Euclidean or Manhattan distance-are problematic especially when used in c ...

We prove that every Schwartz function in Euclidean space can be completely recovered given only its restrictions and the restrictions of its Fourier transform to all origin-centered spheres whose radii are square roots of integers. In particular, the only ...

Collapsing cell complexes was first introduced in the 1930's as a way to deform a space into a topological-equivalent subspace with a sequence of elementary moves. Recently, discrete Morse theory techniques provided an efficient way to construct deformatio ...

We introduce a family of neural quantum states for the simulation of strongly interacting systems in the presence of spatial periodicity. Our variational state is parametrized in terms of a permutationally invariant part described by the Deep Sets neural-n ...

The concept of quasi-symmetry-a perturbatively small deviation from exact symmetry-is introduced and leads to topological materials with strong resilience to perturbations. ...

Sharpness-Aware Minimization (SAM) is a recent training method that relies on worst-case weight perturbations which significantly improves generalization in various settings. We argue that the existing justifications for the success of SAM which are based ...

A General Theory of Equivariant CNNs on Homogeneous Spaces

Chat with Graph Search

Relative, local and global dimension in complex networks

Memory-Based Model Editing at Scale

Block-Sparse Adversarial Attack To Fool Transformer-Based Text Classifiers

Localization errors of the stochastic heat equation

Reduced representations of complexes, signals, and multifiltrations

On discrete Fourier uniqueness sets in Euclidean space

Metric learning for kernel ridge regression: assessment of molecular similarity

Fourier uniqueness and interpolation in Euclidean space

Collapse-invariant properties of spaces equipped with signals or directions

Neural-network quantum states for periodic systems in continuous space

Quasi-symmetry-protected topology in a semi-metal

Towards Understanding Sharpness-Aware Minimization