139 citations · 265 across the 16 of their papers we have counts for
16 papers
Leveraging generative models to assist Monte Carlo sampling
Marylou Gabrié
Sampling high-dimensional probability distributions is a central task in scientific computing, with applications ranging from Bayesian inference to statistical physics and molecula…
A theoretical perspective on mode collapse in variational inference
Roman Soletskyi, Marylou Gabrié, Bruno Loureiro
While deep learning has expanded the possibilities for highly expressive variational families, the practical benefits of these tools for variational inference (VI) are often limite…
Coarse Grained Molecular Dynamics with Normalizing Flows
Samuel Tamagnone, Alessandro Laio, Marylou Gabrié
We propose a sampling algorithm relying on a collective variable (CV) of mid-size dimension modelled by a normalizing flow and using non-equilibrium dynamics to propose full config…
Sampling metastable systems using collective variables and Jarzynski-Crooks paths
Christoph Schönle, Marylou Gabrié, Tony Lelièvre +1
We consider the problem of sampling a high dimensional multimodal target probability measure. We assume that a good proposal kernel to move only a subset of the degrees of freedoms…
Active learning of Boltzmann samplers and potential energies with quantum mechanical accuracy
Ana Molina-Taborda, Pilar Cossio, Olga Lopez-Acevedo +1
Extracting consistent statistics between relevant free-energy minima of a molecular system is essential for physics, chemistry and biology. Molecular dynamics (MD) simulations can…
Balanced Training of Energy-Based Models with Adaptive Flow Sampling
Louis Grenioux, Éric Moulines, Marylou Gabrié
Energy-based models (EBMs) are versatile density estimation models that directly parameterize an unnormalized log density. Although very flexible, EBMs lack a specified normalizati…
On Sampling with Approximate Transport Maps
Louis Grenioux, Alain Durmus, Éric Moulines +1
Transport maps can ease the sampling of distributions with non-trivial geometries by transforming them into distributions that are easier to handle. The potential of this approach…
Adaptive Monte Carlo augmented with normalizing flows
Marylou Gabrié, Grant M. Rotskoff, Eric Vanden-Eijnden
Many problems in the physical sciences, machine learning, and statistical inference necessitate sampling from a high-dimensional, multi-modal probability distribution. Markov Chain…
Phase Retrieval with Holography and Untrained Priors: Tackling the Challenges of Low-Photon Nanoscale Imaging
Hannah Lawrence, David A. Barmherzig, Henry Li +2
Phase retrieval is the inverse problem of recovering a signal from magnitude-only Fourier measurements, and underlies numerous imaging modalities, such as Coherent Diffraction Imag…
Mean-field inference methods for neural networks
Marylou Gabrié
Machine learning algorithms relying on deep neural networks recently allowed a great leap forward in artificial intelligence. Despite the popularity of their applications, the effi…
Blind calibration for compressed sensing: State evolution and an online algorithm
Marylou Gabrié, Jean Barbier, Florent Krzakala +1
Compressed sensing, allows to acquire compressible signals with a small number of measurements. In applications, a hardware implementation often requires a calibration as the sensi…
Entropy and mutual information in models of deep neural networks
Marylou Gabrié, Andre Manoel, Clément Luneau +4
We examine a class of deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) We show how entropies and mutu…
Phase transitions in the -coloring of random hypergraphs
Marylou Gabrié, Varsha Dani, Guilhem Semerjian +1
We study in this paper the structure of solutions in the random hypergraph coloring problem and the phase transitions they undergo when the density of constraints is varied. Hyperg…
A Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines
Eric W. Tramel, Marylou Gabrié, Andre Manoel +2
Restricted Boltzmann machines (RBMs) are energy-based neural-networks which are commonly used as the building blocks for deep architectures neural architectures. In this work, we d…
Inferring Sparsity: Compressed Sensing using Generalized Restricted Boltzmann Machines
Eric W. Tramel, Andre Manoel, Francesco Caltagirone +2
In this work, we consider compressed sensing reconstruction from measurements of -sparse structured signals which do not possess a writable correlation model. Assuming that…
Training Restricted Boltzmann Machines via the Thouless-Anderson-Palmer Free Energy
Marylou Gabrié, Eric W. Tramel, Florent Krzakala
Restricted Boltzmann machines are undirected neural networks which have been shown to be effective in many applications, including serving as initializations for training deep mult…