Masked Autoregressive Flow for Density Estimation
read the original abstract
Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers that the model uses internally when generating data. By constructing a stack of autoregressive models, each modelling the random numbers of the next model in the stack, we obtain a type of normalizing flow suitable for density estimation, which we call Masked Autoregressive Flow. This type of flow is closely related to Inverse Autoregressive Flow and is a generalization of Real NVP. Masked Autoregressive Flow achieves state-of-the-art performance in a range of general-purpose density estimation tasks.
This paper has not been read by Pith yet.
Forward citations
Cited by 16 Pith papers
-
Factorizable Normalizing Flows for parameter-dependent density morphing
Factorizable Normalizing Flows represent parameter-dependent densities via a reference flow composed with a factorized polynomial transformation, enabling isolated per-parameter learning and linear scaling.
-
Testing machine-learned distributions against Monte Carlo data for the QCD chiral phase transition
Conditional MAFs interpolate QCD chiral phase structure across coupling, mass, and volume, reproducing reweighting while cutting required ensembles despite bias near transitions.
-
Inherited or produced? Inferring protein production kinetics when protein counts are shaped by a cell's division history
Conditional normalizing flows approximate intractable likelihoods arising from cell division history to conclude that glc3 is mostly inactive under nutrient stress in yeast, with brief transient expression.
-
Simulation-Based Inference for Cluster Cosmology with Set-Based Neural Network Architectures
SBI framework with GNN-on-sets and masked autoregressive flow recovers input cosmologies from eRASS1 mocks at 11.5% precision on Ω_m and 4.4% on σ_8 using 3259 clusters.
-
Learning the Universe with cosmological rescaling of merger trees and semi-analytic galaxy formation models
Rescaling merger trees with a halo-profile correction enables cheap generation of galaxy summary statistics across cosmologies using semi-analytic models, matching dedicated simulation accuracy with far fewer base runs.
-
GenSBI: Generative Methods for Simulation-Based Inference in JAX
GenSBI delivers JAX-native implementations of generative SBI methods with transformer backbones and reports near-ideal calibration scores on standard benchmarks.
-
Normalizing Flows with Iterative Denoising
iTARFlow augments normalizing flows with diffusion-style iterative denoising during sampling while preserving end-to-end likelihood training, reaching competitive results on ImageNet 64/128/256.
-
Dartmouth Stellar Evolution Emulator (DSEE) 1: Generative Stellar Evolution Model Database
DSEE is a flow-based emulator that generates stellar evolution tracks and isochrones as probabilistic outputs from a single model trained on millions of simulations, enabling fast interpolation and uncertainty-aware analyses.
-
Parameter inference of millilensed gravitational waves using neural spline flows
Neural spline flows perform fast posterior inference on 11-dimensional millilensed GW parameters with accuracy comparable to dynesty for most quantities and a 3-day to 0.8-second speedup.
-
Field-level vs summaries: convergence of information in non-Gaussian density fields
In a controlled model with quadratic nonlinearity, field-level inference retains more parameter information than summaries up to 6-point functions as nonlinearity increases.
-
Machine Learning Techniques for Astrophysics and Cosmology: Photometric Redshifts
AI techniques for photometric redshift estimation have converged and are now limited by the size, systematics, and selection effects in spectroscopic training samples rather than by methodology.
-
Comparative Analysis of EMCEE, Gaussian Process, and Masked Autoregressive Flow in Constraining the Hubble Constant Using Cosmic Chronometers Dataset
EMCEE outperforms GP and MAF in recovering true H0 from mock cosmic chronometer datasets, with GP most sensitive to data points via delete-d jackknife analysis.
-
Application of Machine Learning to 21 cm Cosmology
Review chapter organizing machine learning methods for 21 cm cosmology into observation, theory, and inference domains.
-
Application of Machine Learning to 21 cm Cosmology
A review chapter groups machine learning methods for 21 cm cosmology by their pipeline roles in handling contaminated data, accelerating simulations, and inferring astrophysical parameters.
-
Application of Machine Learning to 21 cm Cosmology
Machine learning helps 21 cm cosmology most when it preserves physically relevant structure and propagates uncertainty explicitly instead of replacing the forward model.
-
Application of Machine Learning to 21 cm Cosmology
Machine learning can address data contamination, accelerate modeling, and aid inference in 21 cm cosmology when it preserves physical structure and uncertainty rather than acting as an opaque replacement.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.