Pith. sign in

REVIEW 21 cited by

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1906.04032 v2 pith:DSOLGYCQ submitted 2019-06-10 stat.ML cs.LG

Neural Spline Flows

classification stat.ML cs.LG
keywords densityflowsautoregressivecouplingflexibilityinvertiblemodelsneural
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the parameterization of an easily invertible elementwise transformation, whose choice determines the flexibility of these models. Building upon recent work, we propose a fully-differentiable module based on monotonic rational-quadratic splines, which enhances the flexibility of both coupling and autoregressive transforms while retaining analytic invertibility. We demonstrate that neural spline flows improve density estimation, variational inference, and generative modeling of images.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 21 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Factorizable Normalizing Flows for parameter-dependent density morphing

    stat.ML 2026-06 unverdicted novelty 7.0

    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.

  2. Dark Matter in Draco and Bo\"otes I: Hints of a Core in an Ultra-Faint Dwarf from Simulation-Based Inference

    astro-ph.GA 2026-06 unverdicted novelty 7.0

    GraphNPE recovers a significantly lower central density for Boötes I consistent with a core while Draco remains marginally cuspy, and demonstrates that higher-order velocity moments reduce bias in dynamical modeling.

  3. Cluster Mass Inference from Galaxy Kinematics

    astro-ph.CO 2026-06 unverdicted novelty 7.0

    Simulation-based Deep Sets model with neural posterior estimation halves scatter in cluster mass estimates from galaxy kinematics compared to the M-sigma relation.

  4. Characterizing Stellar Streams with Error-Aware Machine Learning

    astro-ph.GA 2026-06 unverdicted novelty 7.0

    SCREAM adapts the CATHODE method to treat stellar streams as feature-space over-densities, incorporates measurement uncertainties into neural network training, and achieves F1=0.745 on GD-1 while recovering faint memb...

  5. End-to-End Population Inference from Gravitational-Wave Strain using Transformers

    gr-qc 2026-05 unverdicted novelty 7.0

    Dingo-Pop uses a transformer to perform amortized, end-to-end population inference from GW strain data in seconds, bypassing per-event Monte Carlo sampling.

  6. Data-Driven Predictions for Dark Photon and Millicharged Particle Production

    hep-ph 2025-12 unverdicted novelty 7.0

    A data-driven framework using normalizing flows predicts the rate and kinematic distributions of dark photon and millicharged particle production directly from measured dilepton events.

  7. Inherited or produced? Inferring protein production kinetics when protein counts are shaped by a cell's division history

    q-bio.QM 2025-06 unverdicted novelty 7.0

    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.

  8. Neural posterior estimation of Galactic Binary signals for the LISA mission

    astro-ph.IM 2026-06 unverdicted novelty 6.0

    Conditional normalizing flows perform likelihood-free parameter estimation for single and overlapping LISA galactic binaries, generating thousands of posterior samples per second after training on simulations.

  9. Projecting the ultimate pulsar timing sensitivity to dark matter substructure in a stochastic gravitational wave background

    astro-ph.CO 2026-06 unverdicted novelty 6.0

    Monte Carlo and ML surrogate framework projects PTA sensitivity to compact DM substructures and shows SGWB weakens it, with only Shapiro searches retaining sensitivity in optimistic cases.

  10. GenSBI: Generative Methods for Simulation-Based Inference in JAX

    cs.LG 2026-05 unverdicted novelty 6.0

    GenSBI delivers JAX-native implementations of generative SBI methods with transformer backbones and reports near-ideal calibration scores on standard benchmarks.

  11. Normalizing flows for density estimation in multi-detector gravitational-wave searches

    astro-ph.HE 2026-04 unverdicted novelty 6.0

    Normalizing flows replace binned histograms for estimating multi-detector signal parameters in PyCBC, slashing storage by three orders of magnitude with under 0.05% sensitivity loss and up to 6.55% gains in specific cases.

  12. Tokenised Flow Matching for Hierarchical Simulation Based Inference

    cs.LG 2026-04 unverdicted novelty 6.0

    TFMPE combines likelihood factorisation with tokenised flow matching to enable efficient hierarchical SBI from single-site simulations, producing well-calibrated posteriors at lower computational cost on a new benchma...

  13. Dartmouth Stellar Evolution Emulator (DSEE) 1: Generative Stellar Evolution Model Database

    astro-ph.SR 2026-04 unverdicted novelty 6.0

    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.

  14. Monte Carlo Event Generation with Continuous Normalizing Flows

    hep-ph 2026-04 conditional novelty 6.0

    Continuous normalizing flows improve unweighting efficiency in Monte Carlo event generation for high-jet-multiplicity collider processes by factors up to 184, with wall-time gains of about ten when combined with coupl...

  15. Parameter inference of millilensed gravitational waves using neural spline flows

    gr-qc 2025-05 conditional novelty 6.0

    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.

  16. A search for periodic AGN variability in $\textit{Gaia}$ Data Release 3

    astro-ph.HE 2025-05 accept novelty 6.0

    Systematic search of 377k Gaia DR3 AGN light curves finds no reliable periodic SMBHB candidates after red-noise modeling and empirical false-alarm testing; all survivors lie in the few-cycle regime.

  17. Shap-E: Generating Conditional 3D Implicit Functions

    cs.CV 2023-05 accept novelty 6.0

    Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.

  18. Weakly supervised machine learning for model-agnostic searches of new phenomena in the $\gamma$-ray sky

    astro-ph.HE 2026-07 conditional novelty 5.0

    Weakly supervised classifiers trained on background-versus-mixture samples can identify anomalous gamma-ray sources without labeled signal templates, approaching supervised performance in controlled benchmarks.

  19. Field-level vs summaries: convergence of information in non-Gaussian density fields

    astro-ph.CO 2026-06 unverdicted novelty 5.0

    In a controlled model with quadratic nonlinearity, field-level inference retains more parameter information than summaries up to 6-point functions as nonlinearity increases.

  20. Pre-localization of Massive Black Hole Binaries in the Millihertz Band

    gr-qc 2026-04 unverdicted novelty 5.0

    A neural spline flow pipeline performs amortized inference on millihertz MBHB signals, delivering ~20 deg² pre-merger sky localizations in ~1 minute while matching PTMCMC sky modes and parameter uncertainties.

  21. Assessment of normalizing flows for parameter estimation on time-frequency representations of gravitational-wave data

    gr-qc 2025-05 unverdicted novelty 5.0

    GP15 maps BBH spectrograms to parameter posteriors via residual networks and normalizing flows, producing results consistent with LVK analyses on GWTC-2.1 and GWTC-3 events while running in seconds.