REVIEW 26 cited by
BlackJAX: Composable Bayesian inference in JAX
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
BlackJAX: Composable Bayesian inference in JAX
read the original abstract
BlackJAX is a library implementing sampling and variational inference algorithms commonly used in Bayesian computation. It is designed for ease of use, speed, and modularity by taking a functional approach to the algorithms' implementation. BlackJAX is written in Python, using JAX to compile and run NumpPy-like samplers and variational methods on CPUs, GPUs, and TPUs. The library integrates well with probabilistic programming languages by working directly with the (un-normalized) target log density function. BlackJAX is intended as a collection of low-level, composable implementations of basic statistical 'atoms' that can be combined to perform well-defined Bayesian inference, but also provides high-level routines for ease of use. It is designed for users who need cutting-edge methods, researchers who want to create complex sampling methods, and people who want to learn how these work.
Forward citations
Cited by 26 Pith papers
-
On the triple nature of the PSR J0435+3233 system
PSR J0435+3233 is a hierarchical triple: its anomalous spin-down is an acceleration artifact from a ~1.2 M⊙ outer companion on a ~70-year eccentric orbit.
-
Torus Graphs for Large Scale Neural Phase Analysis
Scalable Torus Graph models with stochastic inference allow large-scale analysis of neural phase couplings and their dynamics in LFP data.
-
gemlib.mcmc: composable kernels for Metropolis-within-Gibbs sampling schemes
gemlib.mcmc supplies composable kernel abstractions for Metropolis-within-Gibbs sampling via writer monads, allowing concise expression and reuse of complex MCMC algorithms for partially observed epidemic models.
-
Rapid Hubble constant inference from GW170817 using GPU-accelerated nested sampling: prior sensitivity and the limits of post-hoc reweighting
Direct sampling under a uniform-in-dL prior raises P(H0>120) from 0.017 to 0.159 for GW170817; post-hoc reweighting recovers only 0.041 because a low-dL mode is undersampled.
-
Binary neutron stars in the next-generation era: Multi-messenger detection prospects and constraints on the equation of state, mass distribution, and cosmology
With ET (and ET+CE), mock multi-messenger BNS catalogues yield ~40–500 EM counterparts per year and, under ideal recovery, constrain R1.4 to ~0.2 km and H0 to ~1 km s−1 Mpc−1.
-
Ab Initio Real-Time Gravitational-Wave Parameter Estimation
Slice-within-Gibbs nested sampling on modern GPUs delivers well-calibrated BNS parameter estimation in ~12 minutes uncompressed and ~89 seconds with heterodyning, from cold priors.
-
Fast, accurate, and differentiable: a neural-network surrogate for NRSur7dq4 precessing binary black hole waveforms
A piecewise MLP surrogate emulates NRSur7dq4 over its full domain at NR-faithful accuracy with ~1 ms GPU latency and a fully differentiable JAX likelihood pipeline.
-
The Universal Warmup Path: Automatic Preconditioner Selection for HMC
A dimension-scheduled multi-chain controller automatically selects diagonal vs low-rank HMC preconditioners from warmup evidence and outperforms fixed Fisher and diagonal baselines on ESS per gradient.
-
SchwarMAX: a GPU-friendly Schwarzschild orbit-superposition modelling framework
SchwarMAX delivers a fast GPU-native Schwarzschild modeling code that recovers density profiles and bar pattern speed from mock IFU data of a simulated barred galaxy.
-
Numerical polology: towards next-generation model-building for cosmology
Numerical polology framework samples coupling space to discover ghost-free tensor field theories up to rank three for cosmology, then applies resulting priors to black hole superradiance, dynamical dark energy, and GW data.
-
Rapid Hubble constant inference from GW170817 using GPU-accelerated nested sampling: prior sensitivity and the limits of post-hoc reweighting
GPU-accelerated nested sampling on GW170817 demonstrates that switching to a uniform-in-dL prior shifts the H0 tail and median far more than post-hoc reweighting captures, due to an under-sampled (dL, iota) bimodality.
-
KiDS-Legacy: Joint analysis of second- and third-order cosmic shear
Joint 2nd- and 3rd-order cosmic shear analysis on KiDS-Legacy data produces Ω_m = 0.297^{+0.056}_{-0.040} and S_8 = 0.806^{+0.025}_{-0.023}, consistent with Planck and prior KiDS results while improving Ω_m precision.
-
Flow-based generative models for amortized Bayesian inference in regression and inverse PDE problems
Flow-ABI trains flow-matching models on historical data to produce a set-conditioned functional posterior sampler that delivers near-real-time Bayesian inference for regression and inverse PDE tasks without per-observ...
-
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.
-
Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics
Tempered sequential Monte Carlo samples from a Boltzmann-tilted distribution over controllers to optimize trajectories and policies under differentiable dynamics.
-
Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics
Tempered sequential Monte Carlo samples efficiently from a temperature-annealed distribution over controller parameters to solve trajectory and policy optimization under differentiable dynamics.
-
Towards E-Value Based Stopping Rules for Bayesian Deep Ensembles
E-value sequential tests enable early stopping of MCMC sampling in Bayesian deep ensembles, often needing only a fraction of the full budget while improving over standard deep ensembles.
-
Global structure of the time delay likelihood
Time delay likelihoods modeled with Gaussian processes develop a boundary-driven W-shape with a global maximum at the true delay and rises at observation window edges, misleading nested sampling and biasing H0 high.
-
Image reconstruction with the JWST Interferometer
Dorito enables diffraction-limited image reconstruction from JWST AMI observations by deconvolving images or Fourier observables using maximum entropy and total variation regularization.
-
Dynamic or Systematic? Bayesian model selection between dark energy and supernova biases
A magnitude offset between low- and high-redshift supernovae beats the Bayesian evidence for flexknot dark energy and reduces DES-5Y/DESI tension.
-
Empirical-Bayes Unfolding of $\gamma$-ray Spectra
Empirical-Bayes hierarchical unfolding for gamma-ray spectra with Poisson ON/OFF likelihood, adaptive Richardson-Lucy prior, and NUTS posterior sampling, yielding spectra consistent with frequentist regularized ML.
-
Star-formation variability on the star-forming main sequence during the Epoch of Reionization
PSD modeling of SFR scatter at six timescales shows dominant variability on 10-30 Myr scales, stronger in lower-mass galaxies at z=3-8.
-
Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models
An importance sampling correction is added to integrated Laplace approximation so that the approximate posterior for latent Gaussian models converges to the true posterior as the number of samples grows.
-
bde: A Python Package for Bayesian Deep Ensembles via MILE
bde is a new Python package that implements Bayesian deep ensembles via efficient JAX-based Microcanonical Langevin Ensembles for tabular regression and classification with uncertainty estimates.
-
Confronting eikonal and post-Kerr methods with numerical evolution of scalar field perturbations in spacetimes beyond Kerr
Numerical simulations benchmark the eikonal and post-Kerr approximations for quasinormal modes in deformed Kerr spacetimes, quantifying their errors relative to expected observational precision.
-
The mass of TOI-1883 b: A low density super-Neptune in the ridge regime transiting an early-M dwarf
Mass of 13.7 Earth masses and density 0.4 g cm^{-3} measured for TOI-1883 b, a super-Neptune in the ridge regime around an early-M dwarf, with implications for disk migration and photoevaporation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.