Masked Autoregressive Flow for Density Estimation

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.

• Publication year

  2017

• Venue

  Neural Information Processing Systems

• Publication date

  2017-05-19

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1705.07057
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• GENERATIVE ADVERSARIAL NETS

  2018cited by this paper
• Maximum Entropy Flow Networks

  2017cited by this paper
• PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications

  2017cited by this paper
• Density estimation using Real NVP

  2016influential reference
• Conditional Image Generation with PixelCNN Decoders

  2016cited by this paper
• Theano: A Python framework for fast computation of mathematical expressions

  2016cited by this paper
• Parameterized neural networks for high-energy physics

  2016cited by this paper
• Improved Variational Inference with Inverse Autoregressive Flow

  2016influential reference
• Inference Compilation and Universal Probabilistic Programming

  2016cited by this paper
• Neural Autoregressive Distribution Estimation

  2016cited by this paper
• Inference Networks for Sequential Monte Carlo in Graphical Models

  2016cited by this paper
• WaveNet: A Generative Model for Raw Audio

  2016cited by this paper
• Pixel Recurrent Neural Networks

  2016cited by this paper
• Fast $\epsilon$-free Inference of Simulation Models with Bayesian Conditional Density Estimation

  2016cited by this paper
• Density Modeling of Images using a Generalized Normalization Transformation

  2015cited by this paper
• Modelling acoustic feature dependencies with artificial neural networks: Trajectory-RNADE

  2015cited by this paper
• MADE: Masked Autoencoder for Distribution Estimation

  2015influential reference
• A note on the evaluation of generative models

  2015cited by this paper
• Generative Image Modeling Using Spatial LSTMs

  2015cited by this paper
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  2015cited by this paper
• Neural Adaptive Sequential Monte Carlo

  2015cited by this paper
• Distilling Intractable Generative Models

  2015cited by this paper
• Variational Inference with Normalizing Flows

  2015influential reference
• Picture: A probabilistic programming language for scene perception

  2015cited by this paper
• Reservoir computing compensates slow response of chemosensor arrays exposed to fast varying gas concentrations in continuous monitoring

  2015cited by this paper
• NICE: Non-linear Independent Components Estimation

  2014influential reference
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models

  2014influential reference
• Auto-Encoding Variational Bayes

  2013influential reference
• A Deep and Tractable Density Estimator

  2013influential reference
• RNADE: The real-valued neural autoregressive density-estimator

  2013cited by this paper
• High-Dimensional Probability Estimation with Deep Density Models

  2013cited by this paper
• Approximate Bayesian computation via regression density estimation

  2012cited by this paper
• Deep Mixtures of Factor Analysers

  2012cited by this paper
• From learning models of natural image patches to whole image restoration

  2011cited by this paper
• Learning Multiple Layers of Features from Tiny Images

  2009cited by this paper
• A Fast Learning Algorithm for Deep Belief Nets

  2006cited by this paper
• The mnist database of handwritten digits

  2005cited by this paper
• Boosted decision trees as an alternative to artificial neural networks for particle identification

  2004cited by this paper
• A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics

  2001cited by this paper
• Gaussianization

  2000cited by this paper

• Conditional Normalizing Flows for Forward and Backward Joint State and Parameter Estimation

  2026cites this paper
• FlexCausal: Flexible Causal Disentanglement via Structural Flow Priors and Manifold-Aware Interventions

  2026cites this paper
• CoVAE: correlated multimodal generative modeling

  2026cites this paper
• Variational Autoencoder with Normalizing flow for X-ray spectral fitting

  2026cites this paper
• Is cosmic birefringence due to dark energy or dark matter? Simulation-based inference

  2026cites this paper
• Predicting galaxy bias using machine learning

  2026cites this paper
• Collective Posterior Inference from Highly Variable Empirical Replicates

  2026cites this paper
• Support Tokens, Stability Margins, and a New Foundation for Robust LLMs

  2026cites this paper
• BayesFlow 2.0: Multi-Backend Amortized Bayesian Inference in Python

  2026cites this paper
• HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data

  2026cites this paper
• TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning

  2026cites this paper
• Frequency-aware priors for variational autoencoders under class imbalance

  2026cites this paper
• Scalable Uncertainty Quantification for Black-Box Density-Based Clustering

  2026cites this paper
• Why the Counterintuitive Phenomenon of Likelihood Rarely Appears in Tabular Anomaly Detection with Deep Generative Models?

  2026cites this paper
• Analytic Bijections for Smooth and Interpretable Normalizing Flows

  2026cites this paper
• Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models

  2026cites this paper
• Minimum Distance Summaries for Robust Neural Posterior Estimation

  2026cites this paper
• Revolutionizing sentiment analysis with generative AI: techniques, trends, and challenges

  2026cites this paper
• Normalizing flows for Bayesian parameter inference in computational mechanics

  2026cites this paper
• An Unsupervised Normalizing Flow-Based Neyman-Pearson Detector for Covert Communications in the Presence of Disco Reconfigurable Intelligent Surfaces

  2026cites this paper
• Risk sensitive twin distributional critics with a lambda lower confidence bound for continuous control reinforcement learning

  2026cites this paper
• A Survey on Missing Data Generation in Networks

  2026cites this paper
• Likelihood-Free Parameter Inference for Spatiotemporal Stochastic Biological Models using Neural Posterior Estimation

  2026cites this paper
• On the global centroid moment tensor achievements and the next generation earthquake catalogs

  2026cites this paper
• It's More Complicated Than You Think: A Forward Model to Infer the Recent Star Formation History, Bursty or Not, of Galaxy Populations

  2026cites this paper
• Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning

  2026influential citation
• On the Reliability of Likelihoods From Conditional Flow Matching Generative Models Trained in Feature Space

  2026cites this paper
• Density-Guided Response Optimization: Community-Grounded Alignment via Implicit Acceptance Signals

  2026cites this paper
• Selecting Optimal Variable Order in Autoregressive Ising Models

  2026cites this paper
• Profiling systematic uncertainties in Simulation-Based Inference with Factorizable Normalizing Flows

  2026cites this paper
• A Bayesian Generative Modeling Approach for Arbitrary Conditional Inference

  2026cites this paper
• In situ estimation of the acoustic surface impedance using simulation-based inferencea).

  2026cites this paper
• Learning at the Edge: Tailed-Uniform Sampling for Robust Simulation-Based Inference

  2026cites this paper
• Joint Inference of Trajectory and Obstacle in Mean-Field Games via Bilevel Optimization

  2025cites this paper
• Neural triangular map for density estimation and sampling with application to Bayesian inference

  2025cites this paper
• Simulation-based population inference of LISA’s Galactic binaries: Bypassing the global fit

  2025cites this paper
• Inherited or produced? Inferring protein production kinetics when protein counts are shaped by a cell’s division history

  2025cites this paper
• Learning Balanced Field Summaries of the Large-Scale Structure with the Neural Field Scattering Transform

  2025cites this paper
• Normalizing flow-enhanced Gaussian embedding for few-shot knowledge graph completion

  2025cites this paper
• Normalizing Flow to Augmented Posterior: Conditional Density Estimation with Interpretable Dimension Reduction for High Dimensional Data

  2025influential citation
• Model Informed Flows for Bayesian Inference of Probabilistic Programs

  2025cites this paper
• DiCoFlex: Model-agnostic diverse counterfactuals with flexible control

  2025cites this paper
• Multilevel neural simulation-based inference

  2025cites this paper
• Wavelet flow for extragalactic foreground simulations

  2025cites this paper
• On-Demand Scenario Generation for Testing Automated Driving Systems

  2025influential citation
• Multi-target property prediction and optimization using latent spaces of generative model

  2025cites this paper
• Multivariate Latent Recalibration for Conditional Normalizing Flows

  2025cites this paper
• Normalizing Flows are Capable Models for RL

  2025cites this paper
• Parameter inference of microlensed gravitational waves using neural spline flows

  2025cites this paper
• Causal Posterior Estimation

  2025cites this paper
• Simulated Annealing ABC with multiple summary statistics

  2025cites this paper
• JAPAN: Joint Adaptive Prediction Areas with Normalising-Flows

  2025cites this paper
• BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models

  2025cites this paper
• Inference Acceleration of Autoregressive Normalizing Flows by Selective Jacobi Decoding

  2025cites this paper
• STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

  2025cites this paper
• Variational Transdimensional Inference

  2025influential citation
• Direct Fisher Score Estimation for Likelihood Maximization

  2025cites this paper
• Data-driven high-dimensional statistical inference with generative models

  2025cites this paper
• Recent Advances in Simulation-based Inference for Gravitational Wave Data Analysis

  2025cites this paper
• Towards characterizing dark matter subhalo perturbations in stellar streams with graph neural networks

  2025cites this paper
• Distilling Normalizing Flows

  2025cites this paper
• Flow Stochastic Segmentation Networks

  2025cites this paper
• Primordial Black Holes and the First Stars

  2025cites this paper
• Latent Thermodynamic Flows: Unified Representation Learning and Generative Modeling of Temperature-Dependent Behaviors from Limited Data

  2025cites this paper
• Distilling Two-Timed Flow Models by Separately Matching Initial and Terminal Velocities

  2025cites this paper
• Mapping global brain reconfigurations following local targeted manipulations

  2025cites this paper
• Generative modelling of multivariate geometric extremes using normalising flows

  2025cites this paper
• A Real-time Anomaly Detection Method for Robots based on a Flexible and Sparse Latent Space

  2025cites this paper
• High-Dimensional Bayesian inference for model updating with neural likelihood approximator powered by dimensionality-reducing flow-based generative model

  2025cites this paper
• Reducing Calls to the Simulator in Simulation Based Inference (SBI)

  2025cites this paper
• Mitigating mode collapse in normalizing flows by annealing with an adaptive schedule: Application to parameter estimation

  2025cites this paper
• RoSMM: A Robust and Secure Multi-Modal Watermarking Framework for Diffusion Models

  2025cites this paper
• InfoMat: Leveraging Information Theory to Visualize and Understand Sequential Data

  2025cites this paper
• Probabilistic Simulation of Aircraft Descent via a Hybrid Physics-Data Approach

  2025cites this paper
• Graphical Transformation Models

  2025cites this paper
• The Big Sobol Sequence : How many simulations do we need for simulation-based inference in cosmology?

  2025cites this paper
• GPDFlow: Generative Multivariate Threshold Exceedance Modeling via Normalizing Flows

  2025cites this paper
• EAGLE: Contextual Point Cloud Generation via Adaptive Continuous Normalizing Flow with Self-Attention

  2025cites this paper
• Solving Schrödinger Bridge Problem via Continuous Normalizing Flow

  2025influential citation
• Wi-CCFAR: Wi-Fi CSI-Based Controllable False Alarm Rate Human Presence Detector With Normalizing Flow

  2025cites this paper
• Combined statistical-biophysical modeling links ion channel genes to physiology of cortical neuron types

  2025cites this paper
• Interpretable Neural Causal Models with TRAM-DAGs

  2025cites this paper
• Continual learning via probabilistic exchangeable sequence modelling

  2025cites this paper
• Paraflow: fast calorimeter simulations parameterized in upstream material configurations

  2025cites this paper
• Time-Series Forecasting via Topological Information Supervised Framework with Efficient Topological Feature Learning

  2025cites this paper
• Virtual Target Trajectory Prediction for Stochastic Targets

  2025cites this paper
• Multi-Flow: Multi-View-Enriched Normalizing Flows for Industrial Anomaly Detection

  2025cites this paper
• Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion Sampling

  2025cites this paper
• Non-parametric prediction of brain MRI microstructure using transfer learning

  2025cites this paper
• Neural Posterior Estimation on Exponential Random Graph Models: Evaluating Bias and Implementation Challenges

  2025cites this paper
• Normalizing Flow Regression for Bayesian Inference with Offline Likelihood Evaluations

  2025cites this paper
• Transforming Simulation to Data Without Pairing

  2025cites this paper
• Image Editing with Diffusion Models: A Survey

  2025cites this paper
• Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models

  2025cites this paper
• Time-DisCo: A Disentangled Contrastive Autoencoder Approach to Enhancing Multivariate Probabilistic Time Series Forecasting From Multisensor Data

  2025cites this paper
• On Measuring Intrinsic Causal Attributions in Deep Neural Networks

  2025cites this paper
• Accelerate TarFlow Sampling with GS-Jacobi Iteration

  2025cites this paper
• Hybrid Bernstein Normalizing Flows for Flexible Multivariate Density Regression with Interpretable Marginals

  2025influential citation
• Improving Anomalous Sound Detection through Pseudo-anomalous Set Selection and Pseudo-label Utilization under Unlabeled Conditions

  2025cites this paper
• Sequential Neural Joint Estimation for likelihood-free inference

  2025cites this paper