EuCAPT white paper: opportunities and challenges for theoretical astroparticle physics in the next decade
RA Batista, MA Amin, G Barenboim, N Bartolo… - arXiv preprint arXiv …, 2021 - arxiv.org
Astroparticle physics is undergoing a profound transformation, due to a series of
extraordinary new results, such as the discovery of high-energy cosmic neutrinos with …
extraordinary new results, such as the discovery of high-energy cosmic neutrinos with …
Disentangling impact of capacity, objective, batchsize, estimators, and step-size on flow VI
A Agrawal, J Domke - arXiv preprint arXiv:2412.08824, 2024 - arxiv.org
Normalizing flow-based variational inference (flow VI) is a promising approximate inference
approach, but its performance remains inconsistent across studies. Numerous algorithmic …
approach, but its performance remains inconsistent across studies. Numerous algorithmic …
PAVI: Plate-Amortized Variational Inference
L Rouillard, AL Bris, T Moreau… - arXiv preprint arXiv …, 2023 - arxiv.org
Given observed data and a probabilistic generative model, Bayesian inference searches for
the distribution of the model's parameters that could have yielded the data. Inference is …
the distribution of the model's parameters that could have yielded the data. Inference is …
Provably Scalable Black-Box Variational Inference with Structured Variational Families
Variational families with full-rank covariance approximations are known not to work well in
black-box variational inference (BBVI), both empirically and theoretically. In fact, recent …
black-box variational inference (BBVI), both empirically and theoretically. In fact, recent …
Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling
Normalizing flows have shown great success as general-purpose density estimators.
However, many real world applications require the use of domain-specific knowledge, which …
However, many real world applications require the use of domain-specific knowledge, which …
Structured variational approximations with skew normal decomposable graphical models and implicit copulas
Although there is much recent work developing flexible variational methods for Bayesian
computation, Gaussian approximations with structured covariance matrices are often …
computation, Gaussian approximations with structured covariance matrices are often …
Understanding and mitigating difficulties in posterior predictive evaluation
A Agrawal, J Domke - arXiv preprint arXiv:2405.19747, 2024 - arxiv.org
Predictive posterior densities (PPDs) are of interest in approximate Bayesian inference.
Typically, these are estimated by simple Monte Carlo (MC) averages using samples from the …
Typically, these are estimated by simple Monte Carlo (MC) averages using samples from the …
Structured variational approximations with skew normal decomposable graphical models
Although there is much recent work developing flexible variational methods for Bayesian
computation, Gaussian approximations with structured covariance matrices are often …
computation, Gaussian approximations with structured covariance matrices are often …
ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models
L Rouillard, D Wassermann - arXiv preprint arXiv:2106.12248, 2021 - arxiv.org
Frequently, population studies feature pyramidally-organized data represented using
Hierarchical Bayesian Models (HBM) enriched with plates. These models can become …
Hierarchical Bayesian Models (HBM) enriched with plates. These models can become …
Bridging Simulation-based Inference and Hierarchical Modeling: Applications in Neuroscience
L Rouillard - 2024 - theses.hal.science
Neuroimaging investigates the brain's architecture and function using magnetic resonance
(MRI). To make sense of the complex observed signal, Neuroscientists posit explanatory …
(MRI). To make sense of the complex observed signal, Neuroscientists posit explanatory …