NumPyro delivers a JIT-compilable iterative NUTS sampler by composing Pyro effect handlers with JAX transformations, achieving faster performance than prior implementations.
hub Mixed citations
Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro
Mixed citation behavior. Most common role is background (60%).
49
Pith papers citing it
Background
60% of classified citations
abstract
NumPyro is a lightweight library that provides an alternate NumPy backend to the Pyro probabilistic programming language with the same modeling interface, language primitives and effect handling abstractions. Effect handlers allow Pyro's modeling API to be extended to NumPyro despite its being built atop a fundamentally different JAX-based functional backend. In this work, we demonstrate the power of composing Pyro's effect handlers with the program transformations that enable hardware acceleration, automatic differentiation, and vectorization in JAX. In particular, NumPyro provides an iterative formulation of the No-U-Turn Sampler (NUTS) that can be end-to-end JIT compiled, yielding an implementation that is much faster than existing alternatives in both the small and large dataset regimes.
hub tools
citation-role summary
background 3
method 2
citation-polarity summary
representative citing papers
acopula enables polynomial-time exact inference for arbitrary nested Archimedean copulas with censoring via Taylor-mode AD on user-defined generators.
A new queryable binary dataset combining cross-build diversity, temporal history, and CVE labels with linked metadata for vulnerability research.
Derives Wasserstein bounds and explicit hyperparameter tuning rules for annealed Langevin dynamics in compositional score-based SBI, proving Linhart et al. (2026) allows larger steps and fewer total steps than Geffner et al. (2023) in the Gaussian case.
Bayesian nonparametric model for dynamic sparse networks with overlapping communities via completely random measures and latent Markov processes.
Large longitudinal RCT finds high rates of following AI personal advice but no sustained well-being gains versus a hobbies control condition.
AMIGO is an end-to-end differentiable forward model of JWST AMI that corrects detector systematics to recover high-precision astrometry and detect close high-contrast companions.
Symbolic regression yields an emulator for the radial Fourier transform of the Sérsic profile that enables 2.5 times faster galaxy profile fitting with minimal accuracy loss.
Introduces HICOBIAN, a differentiable fuzzy hierarchical cosmic-web bias model using sigmoid gradients for smooth region transitions, enabling accurate Bayesian field-level reconstruction of primordial density fields validated by Fourier-space statistics.
Extends NPE to mixed discrete-continuous parameter spaces via a factorized inference network combining an autoregressive classifier and generative model, trained jointly to yield accurate calibrated posteriors.
Variational predictive resampling iteratively imputes data from a variational predictive to produce posterior samples that converge to the exact Bayesian posterior in Gaussian models where mean-field VI retains a gap.
A fully Bayesian pixel-based Doppler imaging framework uses Gaussian Process priors and Hamiltonian Monte Carlo to simultaneously infer surface maps and geometric parameters from spectral data.
ADELIA is the first AD-enabled INLA system that computes exact hyperparameter gradients via a structure-exploiting multi-GPU backward pass, delivering 4.2-7.9x per-gradient speedups and 5-8x better energy efficiency than finite differences on models with up to 1.9 million latent variables.
Massive black hole binary mergers produce orphaned low-frequency signals in PTA pulsar terms that can be stacked for archival multiband gravitational-wave detection.
A differentiable forward model and likelihood enable probabilistic inference over many spatial morphologies for the Galactic Center gamma-ray Excess using variational methods on GPUs.
A parametrized analytical model for BBH mass ratios from the stable mass transfer channel is derived and applied to the 10 solar-mass peak in GWTC-4, favoring little mass-ratio reversal.
AI4BayesCode generates validated modular stateful MCMC samplers from natural language Bayesian model descriptions via LLM translation, modular blocks, and recursive stateful composition.
Combined five-PTA dataset yields posterior on SGWB power-law amplitude and index consistent with nonzero signal but below 5-sigma significance, with reconstructed angular correlations matching the Hellings-Downs prediction.
OzDES final release delivers 62 new reverberation-mapped black hole masses and tighter lag-luminosity relations for Hβ, MgII, and CIV in high-redshift AGN after correcting for survey-length selection effects.
Photon counting readout detects weak postmerger gravitational wave signals at a rate of about 1 in 100 for SNR 0.2 and yields a twofold improvement in neutron star radius measurement after 20,000 events.
Dorito enables diffraction-limited image reconstruction from JWST AMI observations by deconvolving images or Fourier observables using maximum entropy and total variation regularization.
Conversational AI matches self-directed internet search in increasing belief in true political information and decreasing belief in misinformation.
RefineStat improves small language model performance on probabilistic program synthesis by adding semantic constraint enforcement and diagnostic-aware refinement, producing syntactically and statistically reliable code that often matches larger models.
BSA-TNP is a new neural process model with KRBlocks and biased scan attention that claims to match top accuracy while scaling inference to over 1M points in under a minute on a single GPU and supporting translation invariance.
citing papers explorer
-
High-dimensional inference for the $\gamma$-ray sky with differentiable programming
A differentiable forward model and likelihood enable probabilistic inference over many spatial morphologies for the Galactic Center gamma-ray Excess using variational methods on GPUs.
-
The DESI DR1 Peculiar Velocity Survey: growth rate measurements from the maximum likelihood fields method
DESI DR1 peculiar velocity data yields fσ8(z_eff=0.07) = 0.450 ± 0.055, consistent with Planck ΛCDM and GR growth index γ = 0.58 ± 0.11.