REVIEW 34 cited by
Neural Spline Flows
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
Neural Spline Flows
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.
Forward citations
Cited by 34 Pith papers
-
Correlated signals of ultralight scalar dark matter in pulsar timing
A finite-spatial-correlation Gaussian-field prior for PTA ULDM signals interpolates between fully correlated and uncorrelated limits and is validated on blinded mock data for linear and quadratic couplings.
-
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.
-
Dark Matter in Draco and Bo\"otes I: Hints of a Core in an Ultra-Faint Dwarf from Simulation-Based Inference
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.
-
Cluster Mass Inference from Galaxy Kinematics
Simulation-based Deep Sets model with neural posterior estimation halves scatter in cluster mass estimates from galaxy kinematics compared to the M-sigma relation.
-
Characterizing Stellar Streams with Error-Aware Machine Learning
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...
-
End-to-End Population Inference from Gravitational-Wave Strain using Transformers
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.
-
Machine-learning techniques for model-independent searches in dijet final states
Five ML anomaly-detection methods enhance model-agnostic dijet searches at CMS, and a weakly supervised tagger identifies hadronic top-quark decays in data nearly as well as a supervised classifier.
-
Data-Driven Predictions for Dark Photon and Millicharged Particle Production
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.
-
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.
-
A Simulation Based Inference Approach to Modelling of Type Ia Supernova Populations
A simulation-based inference pipeline (Stjörnumál) fits SN Ia dust and intrinsic scatter models to DES 5-year data, enabling fast Bayesian model comparison across seven SN Ia population models.
-
Emulating the complex galactic-scale orbital dynamics of LISA massive black hole pairs with normalizing flows
A normalizing-flow emulator reproduces massive-black-hole decay-time distributions from semi-analytical simulations and, on TNG50 galaxy populations, shows stellar bars reduce binary formation by up to ~5%.
-
LMC-induced Perturbations in the Milky Way Halo II: Bridging Field-level Inference and Summary-level Simulation-Based Inference
A field-level flow-matching likelihood shows the raw 6D halo phase-space distribution carries 2.5-9.9x more MW-LMC parameter information than velocity moments; adding BFE+MOPED summaries recovers much of this gap.
-
Towards anomaly detection searches for new physics signatures including Higgs bosons with weakly supervised machine learning
HAXAD, a weakly supervised anomaly-detection search for Higgs-plus-X new physics, is extended with new embeddings and limit-setting, and on 470 fb^-1 of pseudo-data it matches or exceeds the best single cut-based limi...
-
Search for new scalars via $X \rightarrow SH \rightarrow b\bar{b}b\bar{b}$ in proton-proton collisions at $\sqrt{s} = 13$ TeV with the ATLAS detector
No excess over background is found in ATLAS's first search for X→SH→4b, which sets 95% CL upper limits of 0.7 fb–2.6 pb on the production cross-section times branching ratio.
-
Probabilistic redshift estimation of unresolved galaxies from multi-band background light maps
Conditional normalising flows trained on mock multi-band images recover the redshift distribution of unresolved galaxies with sub-percent accuracy in mean and width, under idealized simulation-matched conditions.
-
Neural posterior estimation of Galactic Binary signals for the LISA mission
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.
-
Projecting the ultimate pulsar timing sensitivity to dark matter substructure in a stochastic gravitational wave background
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.
-
Fortifying gravitational-wave population inference with normalizing flows
Representing each gravitational-wave event's posterior with a normalizing flow lets analysts generate enough cheap posterior samples to keep the Monte-Carlo variance of population inference below threshold for catalog...
-
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 for density estimation in multi-detector gravitational-wave searches
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.
-
Tokenised Flow Matching for Hierarchical Simulation Based Inference
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...
-
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.
-
Monte Carlo Event Generation with Continuous Normalizing Flows
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...
-
MadSpace -- Event Generation for the Era of GPUs and ML
MadSpace is a GPU-native compute-graph event-generation library that matches MadGraph LO physics in validation and introduces the analytic FastRambo phase-space mapping.
-
Analytic Bijections for Smooth and Interpretable Normalizing Flows
Three new analytic bijections and a radial flow architecture give globally smooth, closed-form invertible normalizing flows that match or beat spline baselines on benchmarks and improve phi^4 lattice-field sampling.
-
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.
-
A search for periodic AGN variability in $\textit{Gaia}$ Data Release 3
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.
-
Shap-E: Generating Conditional 3D Implicit Functions
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.
-
Weakly supervised machine learning for model-agnostic searches of new phenomena in the $\gamma$-ray sky
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.
-
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.
-
Pre-localization of Massive Black Hole Binaries in the Millihertz Band
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.
-
Profiling systematic uncertainties in Simulation-Based Inference with Factorizable Normalizing Flows
Systematic uncertainties can be profiled in unbinned likelihood fits by factorizing the normalizing-flow transformation into per-nuisance linear-plus-quadratic terms and training amortized over the nuisance space.
-
Replicating weak-lensing summary-statistic covariances with normalizing flows
Normalizing flows trained on weak-lensing convergence maps reproduce mean and variance of summary statistics to percent level but underestimate off-diagonal covariance by up to 25% unless data augmentation and noise i...
-
Assessment of normalizing flows for parameter estimation on time-frequency representations of gravitational-wave data
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.