Density Estimation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

14 leaderboard tables shown for this task, 14 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 14 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

13 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 498 papers with code (1,394 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Denoising Diffusion Probabilistic Models
  19 Jun 2020 70 repositories listed Syntology ran 178 of 253 samples · 75 unverified · 62 pointer-only (licence)
  We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics.
• Density estimation using Real NVP
  27 May 2016 35 repositories listed Syntology ran 43 of 70 samples · 27 unverified · 33 pointer-only (licence)
  Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning.
• Importance Weighted Autoencoders
  1 Sep 2015 31 repositories listed Syntology ran 13 of 29 samples · 16 unverified · 21 pointer-only (licence)
  The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference.
• Glow: Generative Flow with Invertible 1x1 Convolutions
  9 Jul 2018 27 repositories listed Syntology ran 75 of 129 samples · 54 unverified · 44 pointer-only (licence)
  Flow-based generative models (Dinh et al., 2014) are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and…
• Masked Autoregressive Flow for Density Estimation
  19 May 2017 21 repositories listed Syntology ran 22 of 28 samples · 6 unverified · 9 pointer-only (licence)
  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…
• MADE: Masked Autoencoder for Distribution Estimation
  12 Feb 2015 18 repositories listed Syntology ran 5 of 9 samples · 4 unverified · 1 pointer-only (licence)
  There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples.
• Score-Based Generative Modeling through Stochastic Differential Equations
  26 Nov 2020 15 repositories listed Syntology ran 15 of 23 samples · 8 unverified · 4 pointer-only (licence)
  Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9.
• Conditional Image Generation with PixelCNN Decoders
  16 Jun 2016 14 repositories listed Syntology ran 4 of 14 samples · 10 unverified · 3 pointer-only (licence)
  This work explores conditional image generation with a new image density model based on the PixelCNN architecture.
• Progressive Distillation for Fast Sampling of Diffusion Models
  1 Feb 2022 12 repositories listed Syntology ran 10 of 27 samples · 17 unverified · 10 pointer-only (licence)
  Second, we present a method to distill a trained deterministic diffusion sampler, using many steps, into a new diffusion model that takes half as many sampling steps.
• PointConv: Deep Convolutional Networks on 3D Point Clouds
  17 Nov 2018 9 repositories listed Syntology ran 11 of 15 samples · 4 unverified · 1 pointer-only (licence)
  Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.
• Neural Spline Flows
  10 Jun 2019 8 repositories listed Syntology ran 1 of 3 samples · 2 unverified
  A normalizing flow models a complex probability density as an invertible transformation of a simple base density.
• PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
  19 Jan 2017 8 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  1) We use a discretized logistic mixture likelihood on the pixels, rather than a 256-way softmax, which we find to speed up training.
• Point-Set Registration: Coherent Point Drift
  15 May 2009 8 repositories listed Syntology ran 4 of 9 samples · 5 unverified · 4 pointer-only (licence)
  The goal of point set registration is to assign correspondences between two sets of points and to recover the transformation that maps one point set to the other.
• FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
  2 Oct 2018 7 repositories listed Syntology ran 4 of 5 samples · 1 unverified
  The result is a continuous-time invertible generative model with unbiased density estimation and one-pass sampling, while allowing unrestricted neural network architectures.
• It's Raw! Audio Generation with State-Space Models
  20 Feb 2022 6 repositories listed Syntology ran 6 of 6 samples · 0 unverified · 4 pointer-only (licence)
  SaShiMi yields state-of-the-art performance for unconditional waveform generation in the autoregressive setting.
• Neural Autoregressive Flows
  3 Apr 2018 6 repositories listed Syntology ran 3 of 8 samples · 5 unverified · 2 pointer-only (licence)
  Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art…
• PixelSNAIL: An Improved Autoregressive Generative Model
  28 Dec 2017 6 repositories listed Syntology ran 6 of 7 samples · 1 unverified · 3 pointer-only (licence)
  Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio.
• Representation Learning: A Review and New Perspectives
  24 Jun 2012 6 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors…
• Flow Matching for Generative Modeling
  6 Oct 2022 5 repositories listed Syntology ran 1 of 4 samples · 3 unverified · 3 pointer-only (licence)
  These paths are more efficient than diffusion paths, provide faster training and sampling, and result in better generalization.
• Variational Diffusion Models
  1 Jul 2021 5 repositories listed Syntology ran 29 of 38 samples · 9 unverified · 2 pointer-only (licence)
  In addition, we show that the continuous-time VLB is invariant to the noise schedule, except for the signal-to-noise ratio at its endpoints.
• Temporal Normalizing Flows
  19 Dec 2019 5 repositories listed
  Analyzing and interpreting time-dependent stochastic data requires accurate and robust density estimation.
• Conditional Density Estimation Tools in Python and R with Applications to Photometric Redshifts and Likelihood-Free Cosmological Inference
  30 Aug 2019 5 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  We provide sample code in Python and R as well as examples of applications to photometric redshift estimation and likelihood-free cosmological inference via CDE.
• Invertible Residual Networks
  2 Nov 2018 5 repositories listed Syntology ran 9 of 9 samples · 0 unverified · 3 pointer-only (licence)
  We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation.
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
  2 Nov 2016 5 repositories listed Syntology ran 3 of 5 samples · 2 unverified · 4 pointer-only (licence)
  The essence of the trick is to refactor each stochastic node into a differentiable function of its parameters and a random variable with fixed distribution.
• An Attribute-based Method for Video Anomaly Detection
  1 Dec 2022 4 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Video anomaly detection (VAD) identifies suspicious events in videos, which is critical for crime prevention and homeland security.
• Diagnosing and Fixing Manifold Overfitting in Deep Generative Models
  14 Apr 2022 4 repositories listed
  We propose a class of two-step procedures consisting of a dimensionality reduction step followed by maximum-likelihood density estimation, and prove that they recover the data-generating distribution in the…
• Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series
  16 Feb 2022 4 repositories listed Syntology ran 8 of 24 samples · 16 unverified · 10 pointer-only (licence)
  Anomaly detection is a widely studied task for a broad variety of data types; among them, multiple time series appear frequently in applications, including for example, power grids and traffic networks.
• Densely connected normalizing flows
  8 Jun 2021 4 repositories listed
  Normalizing flows are bijective mappings between inputs and latent representations with a fully factorized distribution.
• Information Theory Measures via Multidimensional Gaussianization
  8 Oct 2020 4 repositories listed
  Information theory is an outstanding framework to measure uncertainty, dependence and relevance in data and systems.
• Graphical Normalizing Flows
  3 Jun 2020 4 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  From this new perspective, we propose the graphical normalizing flow, a new invertible transformation with either a prescribed or a learnable graphical structure.

Syntology lines on 26 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.