Publications by Mario Geiger | EPFL Graph Search

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.

A long-standing goal of science is to accurately simulate large molecular systems using quantum mechanics. The poor scaling of current quantum chemistry algorithms on classical computers, however, imposes an effective limit of about a few dozen atoms on tr ...

Overheating is a common problem both with the use of active and passive solar energy in thermal solar energy systems and in highly glazed buildings, even in central European latitudes. In solar thermal collectors, the elevated temperatures occurring during ...

Glass is a central element to modern architecture and can cover up to 100% of a building façade. The main purpose of large glazed areas is to create bright, comfortable and healthy spaces. It was shown that increasing natural light in offices reduces sickn ...

How many training data are needed to learn a supervised task? It is often observed that the generalization error decreases as n(-beta) where n is the number of training examples and beta is an exponent that depends on both data and algorithm. In this work ...

A novel concept for an advanced fenestration system was studied and samples were produced to demonstrate the feasibility. The resulting novel glazing will combine the functions of daylighting, glare protection, and seasonal thermal control. Coated microstr ...

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 empirical measurements support that it is often not the case. We revisit this qu ...

Deep learning has been immensely successful at a variety of tasks, ranging from classification to artificial intelligence. Learning corresponds to fitting training data, which is implemented by descending a very high-dimensional loss function. Understandin ...

Neural networks (NNs) have been very successful in a variety of tasks ranging from machine translation to image classification. Despite their success, the reasons for their performance are still not well-understood. This thesis explores two main themes: lo ...

Deep learning algorithms are responsible for a technological revolution in a variety oftasks including image recognition or Go playing. Yet, why they work is not understood.Ultimately, they manage to classify data lying in high dimension – a feat generical ...

Two distinct limits for deep learning have been derived as the network width h -> infinity, depending on how the weights of the last layer scale with h. In the neural tangent Kernel (NTK) limit, the dynamics becomes linear in the weights and is described b ...

Advanced optical ray tracing software, CFSpro, was developed for the study and optimization of complex fenestration systems (CFSs). Using an algorithm mixing 2D and 3D approaches, accurate computation of large numbers of rays in extruded geometries can be ...

We analyze numerically the training dynamics of deep neural networks (DNN) by using methods developed in statistical physics of glassy systems. The two main issues we address are (1) the complexity of the loss landscape and of the dynamics within it, and ( ...

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 represent fields on a homogeneous base space, and layers are equivariant ma ...

Supervised deep learning involves the training of neural networks with a large number N of parameters. For large enough N, in the so-called over-parametrized regime, one can essentially fit the training data points. Sparsitybased arguments would suggest th ...

We study how neural networks compress uninformative input space in models where data lie in d dimensions, but the labels of which only vary within a linear manifold of dimension d(parallel to) < d. We show that for a one-hidden-layer network initialized wi ...

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 neural networks uphold Curie's principle and can be used to articulate many sym ...

We analyze numerically the training dynamics of deep neural networks (DNN) by using methods developed in statistical physics of glassy systems. The two main issues we address are the complexity of the loss-landscape and of the dynamics within it, and to wh ...

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 equivariant convolutions to map between such representations. These SE(3)-equiva ...

Mario Geiger

Chat with Graph Search

A recipe for cracking the quantum scaling limit with machine learned electron densities

Thermal solar collector with VO2 absorber coating and V1-xWxO2 thermochromic glazing – Temperature matching and triggering

Towards microstructured glazing for daylighting and thermal control

Asymptotic learning curves of kernel methods: empirical data versus teacher-student paradigm

Embedded microstructures for daylighting and seasonal thermal control

Relative stability toward diffeomorphisms indicates performance in deep nets

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

Loss landscape and symmetries in Neural Networks

Landscape and training regimes in deep learning

Disentangling feature and lazy training in deep neural networks

CFSpro: ray tracing for design and optimization of complex fenestration systems using mixed dimensionality approach

Comparing dynamics: deep neural networks versus glassy systems

Relative stability toward diffeomorphisms indicates performance in deep nets

A General Theory of Equivariant CNNs on Homogeneous Spaces

Scaling description of generalization with number of parameters in deep learning

Geometric compression of invariant manifolds in neural networks

Finding symmetry breaking order parameters with Euclidean neural networks

Comparing Dynamics: Deep Neural Networks versus Glassy Systems

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