
Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training
Deep learning algorithms are responsible for a technological revolution ...
read it

Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties
Equivariant neural networks (ENNs) are graph neural networks embedded in...
read it

Compressing invariant manifolds in neural nets
We study how neural networks compress uninformative input space in model...
read it

Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks
Curie's principle states that "when effects show certain asymmetry, this...
read it

Disentangling feature and lazy learning in deep neural networks: an empirical study
Two distinct limits for deep learning as the net width h→∞ have been pro...
read it

Asymptotic learning curves of kernel methods: empirical data v.s. TeacherStudent paradigm
How many training data are needed to learn a supervised task? It is ofte...
read it

Scaling description of generalization with number of parameters in deep learning
We provide a description for the evolution of the generalization perform...
read it

A General Theory of Equivariant CNNs on Homogeneous Spaces
Group equivariant convolutional neural networks (GCNNs) have recently e...
read it

A jamming transition from under to overparametrization affects loss landscape and generalization
We argue that in fullyconnected networks a phase transition delimits th...
read it

The jamming transition as a paradigm to understand the loss landscape of deep neural networks
Deep learning has been immensely successful at a variety of tasks, rangi...
read it

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
We present a convolutional network that is equivariant to rigid body mot...
read it

Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)
Group equivariant and steerable convolutional neural networks (regular a...
read it

Spherical CNNs
Convolutional Neural Networks (CNNs) have become the method of choice fo...
read it
Mario Geiger
is this you? claim profile