papers

Publications (33)

physics.comp-ph2026

A fast summation method for the DFT-D3 dispersion correction

Victoria Valeeva, Cheuk Hin Ho, Mario Geiger +4

The paper introduces FourierD3, a low‑rank decomposition technique that restores separability in the DFT‑D3 dispersion correction, enabling fast particle‑mesh evaluation in O(N log…

#dispersion correction#density functional theory#fast summation#particle-mesh methods
cs.LG2024

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation

Ameya Daigavane, Song Kim, Mario Geiger +1

We present Symphony, an -equivariant autoregressive generative model for 3D molecular geometries that iteratively builds a molecule from molecular fragments. Existing autoreg…

cs.LG2023

Ophiuchus: Scalable Modeling of Protein Structures through Hierarchical Coarse-graining SO(3)-Equivariant Autoencoders

Allan dos Santos Costa, Ilan Mitnikov, Mario Geiger +3

Three-dimensional native states of natural proteins display recurring and hierarchical patterns. Yet, traditional graph-based modeling of protein structures is often limited to ope…

cs.LG2020

Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks

Tess E. Smidt, Mario Geiger, Benjamin Kurt Miller

Curie's principle states that "when effects show certain asymmetry, this asymmetry must be found in the causes that gave rise to them". We demonstrate that symmetry equivariant neu…

cs.LG2021

Relative stability toward diffeomorphisms indicates performance in deep nets

Leonardo Petrini, Alessandro Favero, Mario Geiger +1

Understanding why deep nets can classify data in large dimensions remains a challenge. It has been proposed that they do so by becoming stable to diffeomorphisms, yet existing empi…

physics.chem-ph2022

Cracking the Quantum Scaling Limit with Machine Learned Electron Densities

Joshua A. Rackers, Lucas Tecot, Mario Geiger +1

A long-standing goal of science is to accurately solve the Schrödinger equation for large molecular systems. The poor scaling of current quantum chemistry algorithms on classical…

cs.LG2025

Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow

Zhonglin Cao, Mario Geiger, Allan dos Santos Costa +6

Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art d…

cs.LG2020

Disentangling feature and lazy training in deep neural networks

Mario Geiger, Stefano Spigler, Arthur Jacot +1

Two distinct limits for deep learning have been derived as the network width , depending on how the weights of the last layer scale with . In the Neural Tan…

cs.LG2022

e3nn: Euclidean Neural Networks

Mario Geiger, Tess Smidt

We present e3nn, a generalized framework for creating E(3) equivariant trainable functions, also known as Euclidean neural networks. e3nn naturally operates on geometry and geometr…

cs.LG2018

Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)

Taco S. Cohen, Mario Geiger, Maurice Weiler

Group equivariant and steerable convolutional neural networks (regular and steerable G-CNNs) have recently emerged as a very effective model class for learning from signal data suc…

cond-mat.dis-nn2019

Scaling description of generalization with number of parameters in deep learning

Mario Geiger, Arthur Jacot, Stefano Spigler +6

Supervised deep learning involves the training of neural networks with a large number of parameters. For large enough , in the so-called over-parametrized regime, one can es…

cs.DC2025

Optimizing Data Distribution and Kernel Performance for Efficient Training of Chemistry Foundation Models: A Case Study with MACE

Jesun Firoz, Franco Pellegrini, Mario Geiger +17

Chemistry Foundation Models (CFMs) that leverage Graph Neural Networks (GNNs) operating on 3D molecular graph structures are becoming indispensable tools for computational chemists…

cs.LG2023

Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning

Antonio Sclocchi, Mario Geiger, Matthieu Wyart

Understanding when the noise in stochastic gradient descent (SGD) affects generalization of deep neural networks remains a challenge, complicated by the fact that networks can oper…

cs.LG2020

A General Theory of Equivariant CNNs on Homogeneous Spaces

Taco Cohen, Mario Geiger, Maurice Weiler

We present a general theory of Group equivariant Convolutional Neural Networks (G-CNNs) on homogeneous spaces such as Euclidean space and the sphere. Feature maps in these networks…

cs.LG2019

A jamming transition from under- to over-parametrization affects loss landscape and generalization

Stefano Spigler, Mario Geiger, Stéphane d'Ascoli +3

We argue that in fully-connected networks a phase transition delimits the over- and under-parametrized regimes where fitting can or cannot be achieved. Under some general condition…

cs.LG2024

EquiJump: Protein Dynamics Simulation via SO(3)-Equivariant Stochastic Interpolants

Allan dos Santos Costa, Ilan Mitnikov, Franco Pellegrini +7

Mapping the conformational dynamics of proteins is crucial for elucidating their functional mechanisms. While Molecular Dynamics (MD) simulation enables detailed time evolution of…

cond-mat.dis-nn2024

Phonon predictions with E(3)-equivariant graph neural networks

Shiang Fang, Mario Geiger, Joseph G. Checkelsky +1

We present an equivariant neural network for predicting vibrational and phonon modes of molecules and periodic crystals, respectively. These predictions are made by evaluating the…

cs.LG2020

Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training

Mario Geiger, Leonardo Petrini, Matthieu Wyart

Deep learning algorithms are responsible for a technological revolution in a variety of tasks including image recognition or Go playing. Yet, why they work is not understood. Ultim…

stat.ML2023

A General Framework for Equivariant Neural Networks on Reductive Lie Groups

Ilyes Batatia, Mario Geiger, Jose Munoz +3

Reductive Lie Groups, such as the orthogonal groups, the Lorentz group, or the unitary groups, play essential roles across scientific fields as diverse as high energy physics, quan…

cs.LG2020

Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties

Benjamin Kurt Miller, Mario Geiger, Tess E. Smidt +1

Equivariant neural networks (ENNs) are graph neural networks embedded in and are well suited for predicting molecular properties. The ENN library e3nn has customizab…

cs.LG2018

Spherical CNNs

Taco S. Cohen, Mario Geiger, Jonas Koehler +1

Convolutional Neural Networks (CNNs) have become the method of choice for learning problems involving 2D planar images. However, a number of problems of recent interest have create…

stat.ML2020

Asymptotic learning curves of kernel methods: empirical data v.s. Teacher-Student paradigm

Stefano Spigler, Mario Geiger, Matthieu Wyart

How many training data are needed to learn a supervised task? It is often observed that the generalization error decreases as where is the number of training examples…

cs.LG2025

BioNeMo Framework: a modular, high-performance library for AI model development in drug discovery

Peter St. John, Dejun Lin, Polina Binder +89

Artificial Intelligence models encoding biology and chemistry are opening new routes to high-throughput and high-quality in-silico drug development. However, their training increas…

physics.comp-ph2021

E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials

Simon Batzner, Albert Musaelian, Lixin Sun +6

This work presents Neural Equivariant Interatomic Potentials (NequIP), an E(3)-equivariant neural network approach for learning interatomic potentials from ab-initio calculations f…

cs.LG2017

Convolutional Networks for Spherical Signals

Taco Cohen, Mario Geiger, Jonas Köhler +1

The success of convolutional networks in learning problems involving planar signals such as images is due to their ability to exploit the translation symmetry of the data distribut…

cs.LG2018

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data

Maurice Weiler, Mario Geiger, Max Welling +2

We present a convolutional network that is equivariant to rigid body motions. The model uses scalar-, vector-, and tensor fields over 3D Euclidean space to represent data, and equi…

cs.LG2025

Proteina: Scaling Flow-based Protein Structure Generative Models

Tomas Geffner, Kieran Didi, Zuobai Zhang +8

Recently, diffusion- and flow-based generative models of protein structures have emerged as a powerful tool for de novo protein design. Here, we develop Proteina, a new large-scale…

astro-ph.GA2019

The Strong Gravitational Lens Finding Challenge

R. Benton Metcalf, M. Meneghetti, Camille Avestruz +33

Large scale imaging surveys will increase the number of galaxy-scale strong lensing candidates by maybe three orders of magnitudes beyond the number known today. Finding these rare…

cs.LG2021

How memory architecture affects learning in a simple POMDP: the two-hypothesis testing problem

Mario Geiger, Christophe Eloy, Matthieu Wyart

Reinforcement learning is generally difficult for partially observable Markov decision processes (POMDPs), which occurs when the agent's observation is partial or noisy. To seek go…

cs.LG2021

Geometric compression of invariant manifolds in neural nets

Jonas Paccolat, Leonardo Petrini, Mario Geiger +2

We study how neural networks compress uninformative input space in models where data lie in dimensions, but whose label only vary within a linear manifold of dimension $d_\para…

physics.chem-ph2021

SE(3)-equivariant prediction of molecular wavefunctions and electronic densities

Oliver T. Unke, Mihail Bogojeski, Michael Gastegger +3

Machine learning has enabled the prediction of quantum chemical properties with high accuracy and efficiency, allowing to bypass computationally costly ab initio calculations. Inst…

eess.IV2024

Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data

Ivan Diaz, Mario Geiger, Richard Iain McKinley

Convolutional neural networks (CNNs) allow for parameter sharing and translational equivariance by using convolutional kernels in their linear layers. By restricting these kernels…

cond-mat.dis-nn2019

The jamming transition as a paradigm to understand the loss landscape of deep neural networks

Mario Geiger, Stefano Spigler, Stéphane d'Ascoli +4

Deep learning has been immensely successful at a variety of tasks, ranging from classification to AI. Learning corresponds to fitting training data, which is implemented by descend…