Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Gilles Louppe

Gilles Louppe

Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks


Jun 06, 2021
Thibaut Théate, Antoine Wehenkel, Adrien Bolland, Gilles Louppe, Damien Ernst

Figure 1 for Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks
Figure 2 for Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks
Figure 3 for Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks
Figure 4 for Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks

  Access Paper or Ask Questions

Leveraging Global Parameters for Flow-based Neural Posterior Estimation


Feb 12, 2021
Pedro L. C. Rodrigues, Thomas Moreau, Gilles Louppe, Alexandre Gramfort

Figure 1 for Leveraging Global Parameters for Flow-based Neural Posterior Estimation
Figure 2 for Leveraging Global Parameters for Flow-based Neural Posterior Estimation
Figure 3 for Leveraging Global Parameters for Flow-based Neural Posterior Estimation
Figure 4 for Leveraging Global Parameters for Flow-based Neural Posterior Estimation

  Access Paper or Ask Questions

QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning


Dec 22, 2020
Pascal Leroy, Damien Ernst, Pierre Geurts, Gilles Louppe, Jonathan Pisane, Matthia Sabatelli

Figure 1 for QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
Figure 2 for QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
Figure 3 for QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
Figure 4 for QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
* To be published in AAAI-21 Workshop on Reinforcement Learning in Games 
  Access Paper or Ask Questions

Towards constraining warm dark matter with stellar streams through neural simulation-based inference


Nov 30, 2020
Joeri Hermans, Nilanjan Banik, Christoph Weniger, Gianfranco Bertone, Gilles Louppe

Figure 1 for Towards constraining warm dark matter with stellar streams through neural simulation-based inference
Figure 2 for Towards constraining warm dark matter with stellar streams through neural simulation-based inference
Figure 3 for Towards constraining warm dark matter with stellar streams through neural simulation-based inference
Figure 4 for Towards constraining warm dark matter with stellar streams through neural simulation-based inference

  Access Paper or Ask Questions

Simulation-efficient marginal posterior estimation with swyft: stop wasting your precious time


Nov 27, 2020
Benjamin Kurt Miller, Alex Cole, Gilles Louppe, Christoph Weniger

Figure 1 for Simulation-efficient marginal posterior estimation with swyft: stop wasting your precious time
Figure 2 for Simulation-efficient marginal posterior estimation with swyft: stop wasting your precious time
Figure 3 for Simulation-efficient marginal posterior estimation with swyft: stop wasting your precious time
Figure 4 for Simulation-efficient marginal posterior estimation with swyft: stop wasting your precious time
* Accepted at Machine Learning and the Physical Sciences at NeurIPS 2020. Package: https://github.com/undark-lab/swyft/ 
  Access Paper or Ask Questions

Lightning-Fast Gravitational Wave Parameter Inference through Neural Amortization


Nov 12, 2020
Arnaud Delaunoy, Antoine Wehenkel, Tanja Hinderer, Samaya Nissanke, Christoph Weniger, Andrew R. Williamson, Gilles Louppe

Figure 1 for Lightning-Fast Gravitational Wave Parameter Inference through Neural Amortization
Figure 2 for Lightning-Fast Gravitational Wave Parameter Inference through Neural Amortization
Figure 3 for Lightning-Fast Gravitational Wave Parameter Inference through Neural Amortization
Figure 4 for Lightning-Fast Gravitational Wave Parameter Inference through Neural Amortization
* V1: First version; V2: Updated references; V3: Update references and camera-ready version 
  Access Paper or Ask Questions

Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference


Nov 11, 2020
Maxime Vandegar, Michael Kagan, Antoine Wehenkel, Gilles Louppe

Figure 1 for Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference
Figure 2 for Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference
Figure 3 for Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference
Figure 4 for Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference

  Access Paper or Ask Questions

Graphical Normalizing Flows


Jun 03, 2020
Antoine Wehenkel, Gilles Louppe

Figure 1 for Graphical Normalizing Flows
Figure 2 for Graphical Normalizing Flows
Figure 3 for Graphical Normalizing Flows
Figure 4 for Graphical Normalizing Flows

  Access Paper or Ask Questions

You say Normalizing Flows I see Bayesian Networks


Jun 03, 2020
Antoine Wehenkel, Gilles Louppe

Figure 1 for You say Normalizing Flows I see Bayesian Networks
Figure 2 for You say Normalizing Flows I see Bayesian Networks
Figure 3 for You say Normalizing Flows I see Bayesian Networks
Figure 4 for You say Normalizing Flows I see Bayesian Networks

  Access Paper or Ask Questions

The frontier of simulation-based inference


Nov 14, 2019
Kyle Cranmer, Johann Brehmer, Gilles Louppe

Figure 1 for The frontier of simulation-based inference
Figure 2 for The frontier of simulation-based inference
Figure 3 for The frontier of simulation-based inference
* v2 fixed typos. 8 pages, 3 figures, proceedings for the Sackler Colloquia at the US National Academy of Sciences 
  Access Paper or Ask Questions

Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning


Oct 17, 2019
Johann Brehmer, Siddharth Mishra-Sharma, Joeri Hermans, Gilles Louppe, Kyle Cranmer

Figure 1 for Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
Figure 2 for Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
Figure 3 for Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
Figure 4 for Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
* 23 pages, 6 figures, code available at https://github.com/smsharma/mining-for-substructure-lens; v2, minor changes to text, version accepted in ApJ 
  Access Paper or Ask Questions

Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms


Sep 01, 2019
Matthia Sabatelli, Gilles Louppe, Pierre Geurts, Marco A. Wiering

Figure 1 for Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms
Figure 2 for Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms
Figure 3 for Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms
Figure 4 for Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms

  Access Paper or Ask Questions

Unconstrained Monotonic Neural Networks


Aug 14, 2019
Antoine Wehenkel, Gilles Louppe

Figure 1 for Unconstrained Monotonic Neural Networks
Figure 2 for Unconstrained Monotonic Neural Networks
Figure 3 for Unconstrained Monotonic Neural Networks
Figure 4 for Unconstrained Monotonic Neural Networks

  Access Paper or Ask Questions

Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale


Jul 08, 2019
Atılım Güneş Baydin, Lei Shao, Wahid Bhimji, Lukas Heinrich, Lawrence Meadows, Jialin Liu, Andreas Munk, Saeid Naderiparizi, Bradley Gram-Hansen, Gilles Louppe, Mingfei Ma, Xiaohui Zhao, Philip Torr, Victor Lee, Kyle Cranmer, Prabhat, Frank Wood

Figure 1 for Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Figure 2 for Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Figure 3 for Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Figure 4 for Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
* 14 pages, 8 figures 
  Access Paper or Ask Questions

Effective LHC measurements with matrix elements and machine learning


Jun 04, 2019
Johann Brehmer, Kyle Cranmer, Irina Espejo, Felix Kling, Gilles Louppe, Juan Pavez

Figure 1 for Effective LHC measurements with matrix elements and machine learning
* Keynote at the 19th International Workshop on Advanced Computing and Analysis Techniques in Physics Research (ACAT 2019) 
  Access Paper or Ask Questions

Likelihood-free MCMC with Approximate Likelihood Ratios


Mar 10, 2019
Joeri Hermans, Volodimir Begy, Gilles Louppe

Figure 1 for Likelihood-free MCMC with Approximate Likelihood Ratios
Figure 2 for Likelihood-free MCMC with Approximate Likelihood Ratios
Figure 3 for Likelihood-free MCMC with Approximate Likelihood Ratios
Figure 4 for Likelihood-free MCMC with Approximate Likelihood Ratios
* 13 pages, 10 figures 
  Access Paper or Ask Questions

Recurrent machines for likelihood-free inference


Nov 30, 2018
Arthur Pesah, Antoine Wehenkel, Gilles Louppe

Figure 1 for Recurrent machines for likelihood-free inference
Figure 2 for Recurrent machines for likelihood-free inference
Figure 3 for Recurrent machines for likelihood-free inference
Figure 4 for Recurrent machines for likelihood-free inference
* NeurIPS 2018 Workshop on Meta-learning (MetaLearn 2018) 
  Access Paper or Ask Questions

Deep Quality-Value (DQV) Learning


Oct 10, 2018
Matthia Sabatelli, Gilles Louppe, Pierre Geurts, Marco A. Wiering

Figure 1 for Deep Quality-Value (DQV) Learning
Figure 2 for Deep Quality-Value (DQV) Learning
Figure 3 for Deep Quality-Value (DQV) Learning

  Access Paper or Ask Questions

Mining gold from implicit models to improve likelihood-free inference


Oct 09, 2018
Johann Brehmer, Gilles Louppe, Juan Pavez, Kyle Cranmer

Figure 1 for Mining gold from implicit models to improve likelihood-free inference
Figure 2 for Mining gold from implicit models to improve likelihood-free inference
Figure 3 for Mining gold from implicit models to improve likelihood-free inference
Figure 4 for Mining gold from implicit models to improve likelihood-free inference
* Code available at https://github.com/johannbrehmer/simulator-mining-example . v2: Fixed typos. v3: Expanded discussion, added Lotka-Volterra example 
  Access Paper or Ask Questions

Adversarial Variational Optimization of Non-Differentiable Simulators


Oct 05, 2018
Gilles Louppe, Joeri Hermans, Kyle Cranmer

Figure 1 for Adversarial Variational Optimization of Non-Differentiable Simulators
Figure 2 for Adversarial Variational Optimization of Non-Differentiable Simulators
Figure 3 for Adversarial Variational Optimization of Non-Differentiable Simulators
Figure 4 for Adversarial Variational Optimization of Non-Differentiable Simulators

  Access Paper or Ask Questions

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model


Sep 01, 2018
Atilim Gunes Baydin, Lukas Heinrich, Wahid Bhimji, Bradley Gram-Hansen, Gilles Louppe, Lei Shao, Prabhat, Kyle Cranmer, Frank Wood

Figure 1 for Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
Figure 2 for Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
Figure 3 for Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
Figure 4 for Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
* 18 pages, 5 figures 
  Access Paper or Ask Questions

Likelihood-free inference with an improved cross-entropy estimator


Aug 02, 2018
Markus Stoye, Johann Brehmer, Gilles Louppe, Juan Pavez, Kyle Cranmer

Figure 1 for Likelihood-free inference with an improved cross-entropy estimator
Figure 2 for Likelihood-free inference with an improved cross-entropy estimator
Figure 3 for Likelihood-free inference with an improved cross-entropy estimator
Figure 4 for Likelihood-free inference with an improved cross-entropy estimator
* 8 pages, 3 figures 
  Access Paper or Ask Questions

A Guide to Constraining Effective Field Theories with Machine Learning


Jul 26, 2018
Johann Brehmer, Kyle Cranmer, Gilles Louppe, Juan Pavez

Figure 1 for A Guide to Constraining Effective Field Theories with Machine Learning
Figure 2 for A Guide to Constraining Effective Field Theories with Machine Learning
Figure 3 for A Guide to Constraining Effective Field Theories with Machine Learning
Figure 4 for A Guide to Constraining Effective Field Theories with Machine Learning
* Phys. Rev. D 98, 052004 (2018) 
 * See also the companion publication "Constraining Effective Field Theories with Machine Learning" at arXiv:1805.00013, a brief introduction presenting the key ideas. The code for these studies is available at https://github.com/johannbrehmer/higgs_inference . v2: Added references. v3: Improved description of algorithms, added references. v4: Clarified text, added references 
  Access Paper or Ask Questions

Constraining Effective Field Theories with Machine Learning


Jul 26, 2018
Johann Brehmer, Kyle Cranmer, Gilles Louppe, Juan Pavez

Figure 1 for Constraining Effective Field Theories with Machine Learning
Figure 2 for Constraining Effective Field Theories with Machine Learning
* Phys. Rev. Lett. 121, 111801 (2018) 
 * See also the companion publication "A Guide to Constraining Effective Field Theories with Machine Learning" at arXiv:1805.00020, an in-depth analysis of machine learning techniques for LHC measurements. The code for these studies is available at https://github.com/johannbrehmer/higgs_inference . v2: New schematic figure explaining the new algorithms, added references. v3, v4: Added references 
  Access Paper or Ask Questions

QCD-Aware Recursive Neural Networks for Jet Physics


Jul 13, 2018
Gilles Louppe, Kyunghyun Cho, Cyril Becot, Kyle Cranmer

Figure 1 for QCD-Aware Recursive Neural Networks for Jet Physics
Figure 2 for QCD-Aware Recursive Neural Networks for Jet Physics
Figure 3 for QCD-Aware Recursive Neural Networks for Jet Physics
Figure 4 for QCD-Aware Recursive Neural Networks for Jet Physics
* 16 pages, 5 figures, 3 appendices, corresponding code at https://github.com/glouppe/recnn 
  Access Paper or Ask Questions