
Leveraging Global Parameters for Flowbased Neural Posterior Estimation
Inferring the parameters of a stochastic model based on experimental obs...
read it

QVMix and QVMixMax: Extending the Deep QualityValue Family of Algorithms to Cooperative MultiAgent Reinforcement Learning
This paper introduces four new algorithms that can be used for tackling ...
read it

Towards constraining warm dark matter with stellar streams through neural simulationbased inference
A statistical analysis of the observed perturbations in the density of s...
read it

Simulationefficient marginal posterior estimation with swyft: stop wasting your precious time
We present algorithms (a) for nested neural likelihoodtoevidence ratio...
read it

Neural Empirical Bayes: Source Distribution Estimation and its Applications to SimulationBased Inference
We revisit empirical Bayes in the absence of a tractable likelihood func...
read it

LightningFast Gravitational Wave Parameter Inference through Neural Amortization
Gravitational waves from compact binaries measured by the LIGO and Virgo...
read it

Graphical Normalizing Flows
Normalizing flows model complex probability distributions by combining a...
read it

You say Normalizing Flows I see Bayesian Networks
Normalizing flows have emerged as an important family of deep neural net...
read it

The frontier of simulationbased inference
Many domains of science have developed complex simulations to describe p...
read it

Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
The subtle and unique imprint of dark matter substructure on extended ar...
read it

Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms
This paper makes one step forward towards characterizing a new family of...
read it

Unconstrained Monotonic Neural Networks
Monotonic neural networks have recently been proposed as a way to define...
read it

Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Probabilistic programming languages (PPLs) are receiving widespread atte...
read it

Effective LHC measurements with matrix elements and machine learning
One major challenge for the legacy measurements at the LHC is that the l...
read it

Likelihoodfree MCMC with Approximate Likelihood Ratios
We propose a novel approach for posterior sampling with intractable like...
read it

Recurrent machines for likelihoodfree inference
Likelihoodfree inference is concerned with the estimation of the parame...
read it

Deep QualityValue (DQV) Learning
We introduce a novel Deep Reinforcement Learning (DRL) algorithm called ...
read it

Likelihoodfree inference with an improved crossentropy estimator
We extend recent work (Brehmer, et. al., 2018) that use neural networks ...
read it

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
We present a novel framework that enables efficient probabilistic infere...
read it

Machine Learning in High Energy Physics Community White Paper
Machine learning is an important research area in particle physics, begi...
read it

Mining gold from implicit models to improve likelihoodfree inference
Simulators often provide the best description of realworld phenomena; h...
read it

Gradient Energy Matching for Distributed Asynchronous Gradient Descent
Distributed asynchronous SGD has become widely used for deep learning in...
read it

A Guide to Constraining Effective Field Theories with Machine Learning
We develop, discuss, and compare several inference techniques to constra...
read it

Constraining Effective Field Theories with Machine Learning
We present powerful new analysis techniques to constrain effective field...
read it

Improvements to Inference Compilation for Probabilistic Programming in LargeScale Scientific Simulators
We consider the problem of Bayesian inference in the family of probabili...
read it

Random Subspace with Trees for Feature Selection Under Memory Constraints
Dealing with datasets of very high dimension is a major challenge in mac...
read it

Adversarial Variational Optimization of NonDifferentiable Simulators
Complex computer simulators are increasingly used across fields of scien...
read it

QCDAware Recursive Neural Networks for Jet Physics
Recent progress in applying machine learning for jet physics has been bu...
read it

Learning to Pivot with Adversarial Networks
Several techniques for domain adaptation have been proposed to account f...
read it

Visualization of Publication Impact
Measuring scholarly impact has been a topic of much interest in recent y...
read it

Contextdependent feature analysis with random forests
In many cases, feature selection is often more complicated than identify...
read it

Ethnicity sensitive author disambiguation using semisupervised learning
Author name disambiguation in bibliographic databases is the problem of ...
read it

Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
In many fields of science, generalized likelihood ratio tests are establ...
read it

Understanding Random Forests: From Theory to Practice
Data analysis and machine learning have become an integrative part of th...
read it

Simple connectome inference from partial correlation statistics in calcium imaging
In this work, we propose a simple yet effective solution to the problem ...
read it
Gilles Louppe
verfied profile
Associate Professor in artificial intelligence and deep learning at the University of Liège