Methods › General › Distribution Approximation › Normalizing Flows
Normalizing Flows
Introduced by Danilo Jimenez Rezende et al. in Variational Inference with Normalizing Flows
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying the rule for change of variables, the initial density ‘flows’ through the sequence of invertible mappings. At the end of this sequence we obtain a valid probability distribution and hence this type of flow is referred to as a normalizing flow.
In the case of finite flows, the basic rule for the transformation of densities considers an invertible, smooth mapping f : ℝᵈ →ℝᵈ with inverse f⁻¹ = g, i.e. the composition g ·f(z) = z. If we use this mapping to transform a random variable z with distribution q(z), the resulting random variable z′ = f(z) has a distribution:
q(z′) = q(z)|det(δf⁻¹)/(δz′)|= q(z)|detδf/δz|⁻¹ where the last equality can be seen by applying the chain rule (inverse function theorem) and is a property of Jacobians of invertible functions. We can construct arbitrarily complex densities by composing several simple maps and successively applying the above equation. The density q_K(z) obtained by successively transforming a random variable z₀ with distribution q₀ through a chain of K transformations fₖ is:
z_K = f_K ·…·f₂ ·f₁(z₀)
lnq_K(z_K) = lnq₀(z₀) − ∑ᴷₖ₌₁ln|detδfₖ/(δzₖ₋₁)| The path traversed by the random variables zₖ = fₖ(zₖ₋₁) with initial distribution q₀(z₀) is called the flow and the path formed by the successive distributions qₖ is a normalizing flow.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 17 in the graph, strongest link: mentioned on GitHub). This answer is about arXiv:1505.05770, the paper the archive credits with this method.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- Argmax Flows · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Argmax Flows') - Grassmann Manifold Flows · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Grassmann Manifold Flows') - Equivariant Manifold Flows · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Equivariant Manifold Flows') - Diffusion Normalizing Flow · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Diffusion Normalizing Flow') - Equivariant Continuous Flows · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Equivariant Continuous Flows') - Energy-Based Normalizing Flow · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Energy-Based Normalizing Flow')
Origin paper of this answer, arXiv:1505.05770 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 21 ran (of which 13 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 1 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 16 unverified (of 37 harvested samples) · 12 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 771 · with a code link: 390 · where Syntology ran a sample: 122 (99 with a run with no instrument failure, 23 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (122 of 771 tagged: 99 with a run with no instrument failure, 23 where every run was a failure of Syntology's instrument)
Page 1 of 8: papers 1 to 100 of 771, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Latent Thermodynamic Flows: Unified Representation Learning and Generative Modeling of Temperature-Dependent Behaviors from Limited Data 3 Jul 2025 · 1 repository · arXiv:2507.03174
-
Distilling Normalizing Flows 26 Jun 2025 · 0 repositories · arXiv:2506.21003
-
ODEₜ (ODEₗ ): Shortcutting the Time and Length in Diffusion and Flow Models for Faster Sampling 26 Jun 2025 · 1 repository · arXiv:2506.21714
-
Time-series surrogates from energy consumers generated by machine learning approaches for long-term forecasting scenarios 25 Jun 2025 · 0 repositories · arXiv:2506.20253
-
Operator Forces For Coarse-Grained Molecular Dynamics 24 Jun 2025 · 1 repository · arXiv:2506.19628
-
Simulating Correlated Electrons with Symmetry-Enforced Normalizing Flows 20 Jun 2025 · 0 repositories · arXiv:2506.17015
-
Latent Noise Injection for Private and Statistically Aligned Synthetic Data Generation 19 Jun 2025 · 0 repositories · arXiv:2506.16636
-
Characterizing Neural Manifolds' Properties and Curvatures using Normalizing Flows 13 Jun 2025 · 0 repositories · arXiv:2506.12187
-
Simulation-trained conditional normalizing flows for likelihood approximation: a case study in stress regulation kinetics in yeast 11 Jun 2025 · 1 repository · arXiv:2506.09374
-
Emulating compact binary population synthesis simulations with robust uncertainty quantification and model comparison: Bayesian normalizing flows 6 Jun 2025 · 1 repository · arXiv:2506.05657
-
Amortized variational transdimensional inference 5 Jun 2025 · 1 repository · arXiv:2506.04749
-
MARBLE: Material Recomposition and Blending in CLIP-Space 5 Jun 2025 · 0 repositories · arXiv:2506.05313
-
Savage-Dickey density ratio estimation with normalizing flows for Bayesian model comparison 4 Jun 2025 · 1 repository · arXiv:2506.04339
-
Asymptotically exact variational flows via involutive MCMC kernels 2 Jun 2025 · 0 repositories · arXiv:2506.02162
-
PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation 1 Jun 2025 · 1 repository · arXiv:2506.01091
-
Quality Assessment of Noisy and Enhanced Speech with Limited Data: UWB-NTIS System for VoiceMOS 2024 and Beyond 31 May 2025 · 0 repositories · arXiv:2506.00506
-
Learning geometry and topology via multi-chart flows 30 May 2025 · 0 repositories · arXiv:2505.24665
-
DiCoFlex: Model-agnostic diverse counterfactuals with flexible control 29 May 2025 · 0 repositories · arXiv:2505.23700
-
Normalizing Flows are Capable Models for RL 29 May 2025 · 1 repository · arXiv:2505.23527
-
SESaMo: Symmetry-Enforcing Stochastic Modulation for Normalizing Flows 26 May 2025 · 0 repositories · arXiv:2505.19619
-
Hybrid Bernstein Normalizing Flows for Flexible Multivariate Density Regression with Interpretable Marginals 20 May 2025 · 2 repositories · arXiv:2505.14164
-
FlowPure: Continuous Normalizing Flows for Adversarial Purification 19 May 2025 · 1 repository · arXiv:2505.13280
-
Minimum-Excess-Work Guidance 19 May 2025 · 0 repositories · arXiv:2505.13375
-
Trustworthy Image Super-Resolution via Generative Pseudoinverse 18 May 2025 · 1 repository · arXiv:2505.12375
-
Path Gradients after Flow Matching 15 May 2025 · 0 repositories · arXiv:2505.10139
-
Continuous Temporal Learning of Probability Distributions via Neural ODEs with Applications in Continuous Glucose Monitoring Data 13 May 2025 · 0 repositories · arXiv:2505.08698
-
Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation 13 May 2025 · 0 repositories · arXiv:2505.08709
-
Hamiltonian Normalizing Flows as kinetic PDE solvers: application to the 1D Vlasov-Poisson Equations 7 May 2025 · 0 repositories · arXiv:2505.04471
-
Physics-Informed Sylvester Normalizing Flows for Bayesian Inference in Magnetic Resonance Spectroscopy 6 May 2025 · 1 repository · arXiv:2505.03590
-
Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation 4 May 2025 · 0 repositories · arXiv:2505.02287
-
A comparison of generative deep learning methods for multivariate angular simulation 28 Apr 2025 · 1 repository · arXiv:2504.21505
-
Efficient Transformed Gaussian Process State-Space Models for Non-Stationary High-Dimensional Dynamical Systems 24 Mar 2025 · 0 repositories · arXiv:2503.18309
-
Augmented Invertible Koopman Autoencoder for long-term time series forecasting 17 Mar 2025 · 1 repository · arXiv:2503.12930
-
GPDFlow: Generative Multivariate Threshold Exceedance Modeling via Normalizing Flows 14 Mar 2025 · 1 repository · arXiv:2503.11822
-
NeuMC -- a package for neural sampling for lattice field theories 14 Mar 2025 · 1 repository · arXiv:2503.11482
-
Characterizing Nonlinear Dynamics via Smooth Prototype Equivalences 13 Mar 2025 · 1 repository · arXiv:2503.10336
-
Flows on convex polytopes 13 Mar 2025 · 1 repository · arXiv:2503.10232
-
Towards Conversational AI for Disease Management 8 Mar 2025 · 0 repositories · arXiv:2503.06074
-
EAGLE: Contextual Point Cloud Generation via Adaptive Continuous Normalizing Flow with Self-Attention 5 Mar 2025 · 1 repository · arXiv:2503.13479
-
Scalable Equilibrium Sampling with Sequential Boltzmann Generators 25 Feb 2025 · 0 repositories · arXiv:2502.18462
-
Flow-based Bayesian filtering for high-dimensional nonlinear stochastic dynamical systems 22 Feb 2025 · 0 repositories · arXiv:2502.16232
-
Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal 15 Feb 2025 · 0 repositories · arXiv:2502.10714
-
Leveraging Constraint Violation Signals For Action-Constrained Reinforcement Learning 8 Feb 2025 · 1 repository · arXiv:2502.10431
-
Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations 8 Feb 2025 · 0 repositories · arXiv:2502.05498
-
Deep Dynamic Probabilistic Canonical Correlation Analysis 7 Feb 2025 · 1 repository · arXiv:2502.05155
-
Bridging the inference gap in Mutimodal Variational Autoencoders 6 Feb 2025 · 0 repositories · arXiv:2502.03952
-
Composite Gaussian Processes Flows for Learning Discontinuous Multimodal Policies 4 Feb 2025 · 0 repositories · arXiv:2502.01913
-
Temperature-Annealed Boltzmann Generators 31 Jan 2025 · 0 repositories · arXiv:2501.19077
-
Can Transformers Learn Full Bayesian Inference in Context? 28 Jan 2025 · 1 repository · arXiv:2501.16825Syntology official (archive's flag): 12 ran · 12 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 16 harvested samples) · 16 pointer-only (licence)
-
Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans 28 Jan 2025 · 0 repositories · arXiv:2501.16839
-
Toward Safe Integration of UAM in Terminal Airspace: UAM Route Feasibility Assessment using Probabilistic Aircraft Trajectory Prediction 28 Jan 2025 · 0 repositories · arXiv:2501.16599
-
GLow -- A Novel, Flower-Based Simulated Gossip Learning Strategy 15 Jan 2025 · 1 repository · arXiv:2501.10463
-
Avoiding subtraction and division of stochastic signals using normalizing flows: NFdeconvolve 14 Jan 2025 · 1 repository · arXiv:2501.08288
-
Keras Sig: Efficient Path Signature Computation on GPU in Keras 3 14 Jan 2025 · 0 repositories · arXiv:2501.08455
-
Simulating the Hubbard Model with Equivariant Normalizing Flows 13 Jan 2025 · 0 repositories · arXiv:2501.07371
-
Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows 6 Jan 2025 · 1 repository · arXiv:2501.03394
-
Bayesian Active Learning By Distribution Disagreement 2 Jan 2025 · 1 repository · arXiv:2501.01248
-
Diverse Rare Sample Generation with Pretrained GANs 27 Dec 2024 · 1 repository · arXiv:2412.19543
-
Stochastic normalizing flows for Effective String Theory 26 Dec 2024 · 0 repositories · arXiv:2412.19109
-
Autoregressive Speech Synthesis with Next-Distribution Prediction 22 Dec 2024 · 0 repositories · arXiv:2412.16846
-
Empirical evaluation of normalizing flows in Markov Chain Monte Carlo 22 Dec 2024 · 3 repositories · arXiv:2412.17136
-
Jet: A Modern Transformer-Based Normalizing Flow 19 Dec 2024 · 0 repositories · arXiv:2412.15129
-
Adaptive Sampling to Reduce Epistemic Uncertainty Using Prediction Interval-Generation Neural Networks 13 Dec 2024 · 1 repository · arXiv:2412.10570
-
ProPLIKS: Probablistic 3D human body pose estimation 5 Dec 2024 · 0 repositories · arXiv:2412.04665
-
Solving High-dimensional Inverse Problems Using Amortized Likelihood-free Inference with Noisy and Incomplete Data 5 Dec 2024 · 0 repositories · arXiv:2412.04565
-
MACAW: A Causal Generative Model for Medical Imaging 3 Dec 2024 · 1 repository · arXiv:2412.02900
-
Scaling of Stochastic Normalizing Flows in SU(3) lattice gauge theory 29 Nov 2024 · 0 repositories · arXiv:2412.00200
-
I See, Therefore I Do: Estimating Causal Effects for Image Treatments 28 Nov 2024 · 0 repositories · arXiv:2412.06810
-
Swarm Intelligence-Driven Client Selection for Federated Learning in Cybersecurity applications 28 Nov 2024 · 0 repositories · arXiv:2411.18877
-
Expert-elicitation method for non-parametric joint priors using normalizing flows 24 Nov 2024 · 1 repository · arXiv:2411.15826Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified (of 11 harvested samples)
-
FLD+: Data-efficient Evaluation Metric for Generative Models 23 Nov 2024 · 1 repository · arXiv:2411.15584
-
Time-Causal VAE: Robust Financial Time Series Generator 5 Nov 2024 · 1 repository · arXiv:2411.02947
-
CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation 28 Oct 2024 · 0 repositories · arXiv:2410.21611
-
Deep Learning Methods for the Noniterative Conditional Expectation G-Formula for Causal Inference from Complex Observational Data 28 Oct 2024 · 0 repositories · arXiv:2410.21531
-
Conditional diffusions for amortized neural posterior estimation 24 Oct 2024 · 1 repository · arXiv:2410.19105Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Unsupervised Low-dose CT Reconstruction with One-way Conditional Normalizing Flows 23 Oct 2024 · 0 repositories · arXiv:2410.17543
-
Parallel Backpropagation for Inverse of a Convolution with Application to Normalizing Flows 18 Oct 2024 · 1 repository · arXiv:2410.14634
-
Continuous normalizing flows for lattice gauge theories 17 Oct 2024 · 0 repositories · arXiv:2410.13161
-
DurIAN-E 2: Duration Informed Attention Network with Adaptive Variational Autoencoder and Adversarial Learning for Expressive Text-to-Speech Synthesis 17 Oct 2024 · 0 repositories · arXiv:2410.13288
-
DFM: Interpolant-free Dual Flow Matching 11 Oct 2024 · 0 repositories · arXiv:2410.09246
-
Normalizing Flow-Based Metric for Image Generation 2 Oct 2024 · 1 repository · arXiv:2410.02004
-
Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows 2 Oct 2024 · 0 repositories · arXiv:2410.01950
-
Stream-level flow matching with Gaussian processes 30 Sep 2024 · 1 repository · arXiv:2409.20423
-
Least Squares and Marginal Log-Likelihood Model Predictive Control using Normalizing Flows 26 Sep 2024 · 0 repositories · arXiv:2409.17632
-
Numerical determination of the width and shape of the effective string using Stochastic Normalizing Flows 24 Sep 2024 · 0 repositories · arXiv:2409.15937
-
AdapFair: Ensuring Continuous Fairness for Machine Learning Operations 23 Sep 2024 · 0 repositories · arXiv:2409.15088
-
For Overall Nighttime Visibility: Integrate Irregular Glow Removal With Glow-Aware Enhancement 23 Sep 2024 · 1 repository
-
Neural Product Importance Sampling via Warp Composition 12 Sep 2024 · 0 repositories · arXiv:2409.18974
-
Rapid Parameter Estimation for Extreme Mass Ratio Inspirals Using Machine Learning 12 Sep 2024 · 0 repositories · arXiv:2409.07957
-
SIG: A Synthetic Identity Generation Pipeline for Generating Evaluation Datasets for Face Recognition 12 Sep 2024 · 0 repositories · arXiv:2409.08345
-
Super Monotonic Alignment Search 12 Sep 2024 · 1 repository · arXiv:2409.07704
-
Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach 10 Sep 2024 · 0 repositories · arXiv:2409.13734
-
CUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networks 6 Sep 2024 · 1 repository · arXiv:2409.04159
-
Can Your Generative Model Detect Out-of-Distribution Covariate Shift? 4 Sep 2024 · 1 repository · arXiv:2409.03043
-
VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization 2 Sep 2024 · 1 repository · arXiv:2409.00942
-
DeepSPoC: A Deep Learning-Based PDE Solver Governed by Sequential Propagation of Chaos 29 Aug 2024 · 0 repositories · arXiv:2408.16403
-
Propagating the prior from shallow to deep with a pre-trained velocity-model Generative Transformer network 19 Aug 2024 · 0 repositories · arXiv:2408.09767
-
Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning 17 Aug 2024 · 0 repositories · arXiv:2408.09125
-
Linear combinations of latents in generative models: subspaces and beyond 16 Aug 2024 · 1 repository · arXiv:2408.08558Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
Open-Source Molecular Processing Pipeline for Generating Molecules 12 Aug 2024 · 0 repositories · arXiv:2408.06261
Tasks archive 2025-07-28
20 shown of 367 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections