REVIEW 24 cited by
Normalizing Flows for Probabilistic Modeling and Inference
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
Normalizing Flows for Probabilistic Modeling and Inference
read the original abstract
Normalizing flows provide a general mechanism for defining expressive probability distributions, only requiring the specification of a (usually simple) base distribution and a series of bijective transformations. There has been much recent work on normalizing flows, ranging from improving their expressive power to expanding their application. We believe the field has now matured and is in need of a unified perspective. In this review, we attempt to provide such a perspective by describing flows through the lens of probabilistic modeling and inference. We place special emphasis on the fundamental principles of flow design, and discuss foundational topics such as expressive power and computational trade-offs. We also broaden the conceptual framing of flows by relating them to more general probability transformations. Lastly, we summarize the use of flows for tasks such as generative modeling, approximate inference, and supervised learning.
Forward citations
Cited by 24 Pith papers
-
Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories
A JEPA-based hypernetwork maps lattice field theory couplings to flow-model weights, and the geometry of those weights recovers the phase transition, intrinsic dimension, and Ising critical exponent of 2D scalar field...
-
Sampling the Schwinger Model with Gauge-Equivariant Diffusion
A gauge-equivariant diffusion model samples Schwinger model configurations, yielding unbiased observables matching MCMC and qualitatively less topological freezing than HMC.
-
One Generator, Any Process: LLM-Conditioning for the LHC
LLM embeddings condition generative networks for LHC events, yielding faster convergence, higher quality, and generalization to unseen processes.
-
Nested-GPT for variable-multiplicity parton showers: A case study in the resummation of non-global logarithms
Nested-GPT is an autoregressive Transformer that dynamically generates variable-multiplicity parton showers matching Monte Carlo references for non-global logarithm resummation in the large-Nc limit.
-
Nested-GPT for variable-multiplicity parton showers: A case study in the resummation of non-global logarithms
Nested-GPT is an autoregressive Transformer surrogate that generates variable-multiplicity parton showers while enforcing ordered Markovian branching and matches reference Monte Carlo results for leading-log non-globa...
-
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.
-
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.
-
Particle-based Energetic Variational Inference
Energetic variational inference derives existing particle-based VI methods from energy-dissipation laws and proposes an approximation-then-variation scheme that preserves particle-level structure while reducing KL divergence.
-
Transformers with Physics-Informed Encodings and Simulation-Based Inference for Robust Detection of Eccentric Binary Black Holes in Pulsar Timing Array Data
Physics-informed Transformer encodings plus conditional normalizing flows yield sharper, better-calibrated posteriors for eccentric BBHs in white-noise PTA data than physics-agnostic SBI baselines.
-
Simulation-Based Inference for Cluster Cosmology with Set-Based Neural Network Architectures
SBI framework with GNN-on-sets and masked autoregressive flow recovers input cosmologies from eRASS1 mocks at 11.5% precision on Ω_m and 4.4% on σ_8 using 3259 clusters.
-
One Generator, Any Process: LLM-Conditioning for the LHC
LLM embeddings condition a generative transformer to enable faster convergence, better performance, and generalization to unseen LHC processes using a single model.
-
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.
-
Learning the Universe with cosmological rescaling of merger trees and semi-analytic galaxy formation models
Rescaling merger trees with a one-parameter halo-profile correction plus a semi-analytic model matches dedicated N-body suites for Ω_m and σ_8 inference at a fraction of the cost.
-
Learning the Universe with cosmological rescaling of merger trees and semi-analytic galaxy formation models
Rescaling merger trees with a halo-profile correction enables cheap generation of galaxy summary statistics across cosmologies using semi-analytic models, matching dedicated simulation accuracy with far fewer base runs.
-
Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions
Generative models for cosmological field-level inference can reproduce posterior means and cross-correlations yet fail to capture correct uncertainty geometry when validated against HMC reference samples.
-
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.
-
Application of a Mixture of Experts-based Foundation Model to the GlueX DIRC Detector
A single MoE-based foundation model with transformer backbone unifies simulation, PID, and noise filtering for the GlueX DIRC detector and matches or exceeds traditional geometrical and prior deep-learning methods acr...
-
Inferring the population properties of galactic binaries from LISA's stochastic foreground
A neural posterior estimator trained on simulated LISA foreground spectra recovers galactic binary population parameters, including total number, with good accuracy in validation tests.
-
Gravitational-Wave Parameter Estimation in non-Gaussian noise using Score-Based Likelihood Characterization
Score-based diffusion models learn the empirical distribution of real LIGO noise to enable unbiased gravitational-wave parameter estimation under only an additivity assumption.
-
Evidence for eccentricity in the population of binary black holes observed by LIGO-Virgo-KAGRA
Bayesian inference on LVK O1-O3 events with eccentric aligned-spin waveforms yields log10 Bayes factors of 1.77-4.75 favoring eccentricity for GW200129, GW190701 and GW200208_22, and >99.5% probability that at least o...
-
Pulse profile modelling of the 2024 outburst of the accreting millisecond pulsar SRGA J144459.2-604207
Joint NICER+IXPE pulse-profile modeling of SRGA J144459.2-604207 favors large neutron-star mass and radius with two independent hotspots but shows strong sensitivity to joint-analysis methodology.
-
On the Presence of a Tertiary Compact Object in GW190814
Extended-data Bayesian reanalysis of GW190814 finds no evidence for tertiary-induced line-of-sight acceleration or residual eccentricity due to strong degeneracy between the two effects.
-
Machine Learning Techniques for Astrophysics and Cosmology: Photometric Redshifts
AI techniques for photometric redshift estimation have converged and are now limited by the size, systematics, and selection effects in spectroscopic training samples rather than by methodology.
-
Machine Learning Techniques for Astrophysics and Cosmology: Lyman-$\alpha$ forest
Review of machine learning applications for analyzing Lyman-alpha forest observations to probe cosmology, reionization, and dark matter.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.