Search Results for author:
Found 59 papers, 43 papers with code
Harnessing machine learning for accurate treatment of overlapping opacity species in general circulation models
For this study, we specifically examined the coupling between chemistry and radiation in GCMs and compared different methods for the mixing of opacities of different chemical species in the correlated-k assumption, when equilibrium chemistry cannot be assumed.
Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability
Bayesian inference allows expressing the uncertainty of posterior belief under a probabilistic model given prior information and the likelihood of the evidence.
Robust Ocean Subgrid-Scale Parameterizations Using Fourier Neural Operators
In climate simulations, small-scale processes shape ocean dynamics but remain computationally expensive to resolve directly.
Score-based Data Assimilation for a Two-Layer Quasi-Geostrophic Model
Data assimilation addresses the problem of identifying plausible state trajectories of dynamical systems given noisy or incomplete observations.
Dynamic NeRFs for Soccer Scenes
The long-standing problem of novel view synthesis has many applications, notably in sports broadcasting.
Score-based Data Assimilation
Data assimilation, in its most comprehensive form, addresses the Bayesian inverse problem of identifying plausible state trajectories that explain noisy or incomplete observations of stochastic dynamical systems.
Policy Gradient Algorithms Implicitly Optimize by Continuation
First, we formulate direct policy optimization in the optimization by continuation framework.
Balancing Simulation-based Inference for Conservative Posteriors
We show empirically that the balanced versions tend to produce conservative posterior approximations on a wide variety of benchmarks.
Implicit representation priors meet Riemannian geometry for Bayesian robotic grasping
Robotic grasping in highly noisy environments presents complex challenges, especially with limited prior knowledge about the scene.
Graph-informed simulation-based inference for models of active matter
Moreover, we demonstrate that a small number (from one to three) snapshots of the system can be used for parameter inference and that this graph-informed approach outperforms typical metrics such as the average velocity or mean square displacement of the system.
Simulation-based Bayesian inference for robotic grasping
General robotic grippers are challenging to control because of their rich nonsmooth contact dynamics and the many sources of uncertainties due to the environment or sensor noise.
Adaptive Self-Training for Object Detection
In this work, we introduce our method Adaptive Self-Training for Object Detection (ASTOD), which is a simple yet effective teacher-student method.
Ranked #11 on
Semi-Supervised Object Detection
on COCO 2% labeled data
Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation
In this work, we introduce Balanced Neural Ratio Estimation (BNRE), a variation of the NRE algorithm designed to produce posterior approximations that tend to be more conservative, hence improving their reliability, while sharing the same Bayes optimal solution.
Robust Hybrid Learning With Expert Augmentation
Hybrid modelling reduces the misspecification of expert models by combining them with machine learning (ML) components learned from data.
SAE: Sequential Anchored Ensembles
Anchored ensembles approximate the posterior by training an ensemble of neural networks on anchored losses designed for the optima to follow the Bayesian posterior.
From global to local MDI variable importances for random forests and when they are Shapley values
Random forests have been widely used for their ability to provide so-called importance measures, which give insight at a global (per dataset) level on the relevance of input variables to predict a certain output.
A Trust Crisis In Simulation-Based Inference? Your Posterior Approximations Can Be Unfaithful
We present extensive empirical evidence showing that current Bayesian simulation-based inference algorithms can produce computationally unfaithful posterior approximations.
Arbitrary Marginal Neural Ratio Estimation for Simulation-based Inference
In many areas of science, complex phenomena are modeled by stochastic parametric simulators, often featuring high-dimensional parameter spaces and intractable likelihoods.
Simulation-based Bayesian inference for multi-fingered robotic grasping
Multi-fingered robotic grasping is an undeniable stepping stone to universal picking and dexterous manipulation.
Truncated Marginal Neural Ratio Estimation
Parametric stochastic simulators are ubiquitous in science, often featuring high-dimensional input parameters and/or an intractable likelihood.
Diffusion Priors In Variational Autoencoders
Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling.
Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks
The results highlight the main strengths and weaknesses associated with each probability metric together with an important limitation of the Wasserstein distance.
Distributional Reinforcement Learning
reinforcement-learning
+2
HNPE: Leveraging Global Parameters for Neural Posterior Estimation
Inferring the parameters of a stochastic model based on experimental observations is central to the scientific method.
QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
This paper introduces four new algorithms that can be used for tackling multi-agent reinforcement learning (MARL) problems occurring in cooperative settings.
Towards constraining warm dark matter with stellar streams through neural simulation-based inference
A statistical analysis of the observed perturbations in the density of stellar streams can in principle set stringent contraints on the mass function of dark matter subhaloes, which in turn can be used to constrain the mass of the dark matter particle.
Simulation-efficient marginal posterior estimation with swyft: stop wasting your precious time
We present algorithms (a) for nested neural likelihood-to-evidence ratio estimation, and (b) for simulation reuse via an inhomogeneous Poisson point process cache of parameters and corresponding simulations.
Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference
We revisit empirical Bayes in the absence of a tractable likelihood function, as is typical in scientific domains relying on computer simulations.
Lightning-Fast Gravitational Wave Parameter Inference through Neural Amortization
Gravitational waves from compact binaries measured by the LIGO and Virgo detectors are routinely analyzed using Markov Chain Monte Carlo sampling algorithms.
Graphical Normalizing Flows
From this new perspective, we propose the graphical normalizing flow, a new invertible transformation with either a prescribed or a learnable graphical structure.
You say Normalizing Flows I see Bayesian Networks
Normalizing flows have emerged as an important family of deep neural networks for modelling complex probability distributions.
The frontier of simulation-based inference
Many domains of science have developed complex simulations to describe phenomena of interest.
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 arcs in strong lensing systems contains a wealth of information about the properties and distribution of dark matter on small scales and, consequently, about the underlying particle physics.
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 \textit{model-free} Deep Reinforcement Learning (DRL) algorithms.
Unconstrained Monotonic Neural Networks
Monotonic neural networks have recently been proposed as a way to define invertible transformations.
Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Probabilistic programming languages (PPLs) are receiving widespread attention for performing Bayesian inference in complex generative models.
Effective LHC measurements with matrix elements and machine learning
One major challenge for the legacy measurements at the LHC is that the likelihood function is not tractable when the collected data is high-dimensional and the detector response has to be modeled.
Likelihood-free MCMC with Amortized Approximate Ratio Estimators
This work introduces a novel approach to address the intractability of the likelihood and the marginal model.
Recurrent machines for likelihood-free inference
Likelihood-free inference is concerned with the estimation of the parameters of a non-differentiable stochastic simulator that best reproduce real observations.
Deep Quality-Value (DQV) Learning
We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning.
Likelihood-free inference with an improved cross-entropy estimator
We extend recent work (Brehmer, et.
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
We present a novel probabilistic programming framework that couples directly to existing large-scale simulators through a cross-platform probabilistic execution protocol, which allows general-purpose inference engines to record and control random number draws within simulators in a language-agnostic way.
Machine Learning in High Energy Physics Community White Paper
In this document we discuss promising future research and development areas for machine learning in particle physics.
BIG-bench Machine Learning
Vocal Bursts Intensity Prediction
Mining gold from implicit models to improve likelihood-free inference
Simulators often provide the best description of real-world phenomena.
Gradient Energy Matching for Distributed Asynchronous Gradient Descent
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.
A Guide to Constraining Effective Field Theories with Machine Learning
We develop, discuss, and compare several inference techniques to constrain theory parameters in collider experiments.
Constraining Effective Field Theories with Machine Learning
We present powerful new analysis techniques to constrain effective field theories at the LHC.
Improvements to Inference Compilation for Probabilistic Programming in Large-Scale Scientific Simulators
We consider the problem of Bayesian inference in the family of probabilistic models implicitly defined by stochastic generative models of data.
Random Subspace with Trees for Feature Selection Under Memory Constraints
Dealing with datasets of very high dimension is a major challenge in machine learning.
Adversarial Variational Optimization of Non-Differentiable Simulators
We adapt the training procedure of generative adversarial networks by replacing the differentiable generative network with a domain-specific simulator.
QCD-Aware Recursive Neural Networks for Jet Physics
Recent progress in applying machine learning for jet physics has been built upon an analogy between calorimeters and images.
Learning to Pivot with Adversarial Networks
Several techniques for domain adaptation have been proposed to account for differences in the distribution of the data used for training and testing.
Context-dependent feature analysis with random forests
In many cases, feature selection is often more complicated than identifying a single subset of input variables that would together explain the output.
Ethnicity sensitive author disambiguation using semi-supervised learning
Author name disambiguation in bibliographic databases is the problem of grouping together scientific publications written by the same person, accounting for potential homonyms and/or synonyms.
Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
This leads to a new machine learning-based approach to likelihood-free inference that is complementary to Approximate Bayesian Computation, and which does not require a prior on the model parameters.
Understanding Random Forests: From Theory to Practice
In the second part of this work, we analyse and discuss the interpretability of random forests in the eyes of variable importance measures.
Simple connectome inference from partial correlation statistics in calcium imaging
In this work, we propose a simple yet effective solution to the problem of connectome inference in calcium imaging data.
Understanding variable importances in forests of randomized trees
Despite growing interest and practical use in various scientific areas, variable importances derived from tree-based ensemble methods are not well understood from a theoretical point of view.
API design for machine learning software: experiences from the scikit-learn project
Scikit-learn is an increasingly popular machine learning li- brary.
Scikit-learn: Machine Learning in Python
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.
