63.6k citations · 68k across the 67 of their papers we have counts for
21 papers · 1 filter
An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning
Maximilian Dax, Theo Heimel, Gilles Louppe
Simulation-based inference (SBI) with machine learning is an increasingly important tool for solving inverse problems in science and engineering, including parameter inference and…
Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation
Gérôme Andry, Sacha Lewin, François Rozet +6
Deep learning has advanced weather forecasting, but accurate predictions first require identifying the current state of the atmosphere from observational data. In this work, we int…
Learning Diffusion Priors from Observations by Expectation Maximization
François Rozet, Gérôme Andry, François Lanusse +1
Diffusion models recently proved to be remarkable priors for Bayesian inverse problems. However, training these models typically requires access to large amounts of clean data, whi…
Robust Ocean Subgrid-Scale Parameterizations Using Fourier Neural Operators
Victor Mangeleer, Gilles Louppe
In climate simulations, small-scale processes shape ocean dynamics but remain computationally expensive to resolve directly. For this reason, their contributions are commonly appro…
Score-based Data Assimilation
François Rozet, Gilles Louppe
Data assimilation, in its most comprehensive form, addresses the Bayesian inverse problem of identifying plausible state trajectories that explain noisy or incomplete observations…
Policy Gradient Algorithms Implicitly Optimize by Continuation
Adrien Bolland, Gilles Louppe, Damien Ernst
Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper…
Robust Hybrid Learning With Expert Augmentation
Antoine Wehenkel, Jens Behrmann, Hsiang Hsu +3
Hybrid modelling reduces the misspecification of expert models by combining them with machine learning (ML) components learned from data. Similarly to many ML algorithms, hybrid mo…
SAE: Sequential Anchored Ensembles
Arnaud Delaunoy, Gilles Louppe
Computing the Bayesian posterior of a neural network is a challenging task due to the high-dimensionality of the parameter space. Anchored ensembles approximate the posterior by tr…
Arbitrary Marginal Neural Ratio Estimation for Simulation-based Inference
François Rozet, Gilles Louppe
In many areas of science, complex phenomena are modeled by stochastic parametric simulators, often featuring high-dimensional parameter spaces and intractable likelihoods. In this…
Diffusion Priors In Variational Autoencoders
Antoine Wehenkel, Gilles Louppe
Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling. However, VAEs are a…
Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks
Thibaut Théate, Antoine Wehenkel, Adrien Bolland +2
The distributional reinforcement learning (RL) approach advocates for representing the complete probability distribution of the random return instead of only modelling its expectat…
QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
Pascal Leroy, Damien Ernst, Pierre Geurts +3
This paper introduces four new algorithms that can be used for tackling multi-agent reinforcement learning (MARL) problems occurring in cooperative settings. All algorithms are bas…
You say Normalizing Flows I see Bayesian Networks
Antoine Wehenkel, Gilles Louppe
Normalizing flows have emerged as an important family of deep neural networks for modelling complex probability distributions. In this note, we revisit their coupling and autoregre…
Graphical Normalizing Flows
Antoine Wehenkel, Gilles Louppe
Normalizing flows model complex probability distributions by combining a base distribution with a series of bijective neural networks. State-of-the-art architectures rely on coupli…
Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms
Matthia Sabatelli, Gilles Louppe, Pierre Geurts +1
This paper makes one step forward towards characterizing a new family of \textit{model-free} Deep Reinforcement Learning (DRL) algorithms. The aim of these algorithms is to jointly…
Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Atılım Güneş Baydin, Lei Shao, Wahid Bhimji +14
Probabilistic programming languages (PPLs) are receiving widespread attention for performing Bayesian inference in complex generative models. However, applications to science remai…
Unconstrained Monotonic Neural Networks
Antoine Wehenkel, Gilles Louppe
Monotonic neural networks have recently been proposed as a way to define invertible transformations. These transformations can be combined into powerful autoregressive flows that h…
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
Atılım Güneş Baydin, Lukas Heinrich, Wahid Bhimji +12
We present a novel probabilistic programming framework that couples directly to existing large-scale simulators through a cross-platform probabilistic execution protocol, which all…
Gradient Energy Matching for Distributed Asynchronous Gradient Descent
Joeri Hermans, Gilles Louppe
Distributed asynchronous SGD has become widely used for deep learning in large-scale systems, but remains notorious for its instability when increasing the number of workers. In th…
API design for machine learning software: experiences from the scikit-learn project
Lars Buitinck, Gilles Louppe, Mathieu Blondel +12
Scikit-learn is an increasingly popular machine learning li- brary. Written in Python, it is designed to be simple and efficient, accessible to non-experts, and reusable in various…
Scikit-learn: Machine Learning in Python
Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort +16
Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses…