Recognition: unknown
Variational Inference with Normalizing Flows
read the original abstract
The choice of approximate posterior distribution is one of the core problems in variational inference. Most applications of variational inference employ simple families of posterior approximations in order to allow for efficient inference, focusing on mean-field or other simple structured approximations. This restriction has a significant impact on the quality of inferences made using variational methods. We introduce a new approach for specifying flexible, arbitrarily complex and scalable approximate posterior distributions. Our approximations are distributions constructed through a normalizing flow, whereby a simple initial density is transformed into a more complex one by applying a sequence of invertible transformations until a desired level of complexity is attained. We use this view of normalizing flows to develop categories of finite and infinitesimal flows and provide a unified view of approaches for constructing rich posterior approximations. We demonstrate that the theoretical advantages of having posteriors that better match the true posterior, combined with the scalability of amortized variational approaches, provides a clear improvement in performance and applicability of variational inference.
This paper has not been read by Pith yet.
Forward citations
Cited by 10 Pith papers
-
Neural Ordinary Differential Equations
Neural networks are redefined as continuous dynamical systems by learning the derivative of the hidden state with a neural network and integrating it with an ODE solver.
-
Density estimation using Real NVP
Real NVP uses affine coupling layers to create invertible transformations that support exact density estimation, sampling, and latent inference without approximations.
-
Testing machine-learned distributions against Monte Carlo data for the QCD chiral phase transition
Conditional MAFs interpolate QCD chiral phase structure across coupling, mass, and volume, reproducing reweighting while cutting required ensembles despite bias near transitions.
-
Information as Maximum-Caliber Deviation: A bridge between Integrated Information Theory and the Free Energy Principle
Information defined as maximum-caliber deviation derives IIT 3.0 cause-effect repertoires from constrained entropy maximization and equates to prediction error under CLT and LDT.
-
ML for the hKLM at the 2nd Detector
Graph neural networks trained on simulated hits outperform classical methods for energy resolution, timing, and particle identification in an iron-scintillator sampling calorimeter, with an integrated multi-objective ...
-
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Hugging Face releases an open-source Python library that supplies a unified API and pretrained weights for major Transformer architectures used in natural language processing.
-
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.
-
Machine Learning Techniques for Astrophysics and Cosmology: Simulation-Based Inference
Simulation-based inference uses neural networks trained on simulations to enable parameter inference in cosmology and astrophysics where traditional likelihood calculations are intractable.
-
Application of Machine Learning to 21 cm Cosmology
Machine learning helps 21 cm cosmology most when it preserves physically relevant structure and propagates uncertainty explicitly instead of replacing the forward model.
-
Application of Machine Learning to 21 cm Cosmology
Machine learning can address data contamination, accelerate modeling, and aid inference in 21 cm cosmology when it preserves physical structure and uncertainty rather than acting as an opaque replacement.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.