Sylvester Normalizing Flows for Variational Inference

Variational inference relies on flexible approximate posterior distributions. Normalizing flows provide a general recipe to construct flexible variational posteriors. We introduce Sylvester normalizing flows, which can be seen as a generalization of planar flows. Sylvester normalizing flows remove the well-known single-unit bottleneck from planar flows, making a single transformation much more flexible. We compare the performance of Sylvester normalizing flows against planar flows and inverse autoregressive flows and demonstrate that they compare favorably on several datasets.

• Publication year

  2018

• Venue

  Conference on Uncertainty in Artificial Intelligence

• Publication date

  2018-03-15

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1803.05649
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• AUTO-ENCODING VARIATIONAL BAYES

  2020influential reference
• Variational Inference with Orthogonal Normalizing Flows

  2017cited by this paper
• Masked Autoregressive Flow for Density Estimation

  2017cited by this paper
• HyperNetworks

  2016cited by this paper
• Density estimation using Real NVP

  2016influential reference
• Ladder Variational Autoencoders

  2016cited by this paper
• Approximate Inference for Deep Latent Gaussian Mixtures

  2016cited by this paper
• Improved Variational Inference with Inverse Autoregressive Flow

  2016cited by this paper
• Improving Variational Auto-Encoders using Householder Flow

  2016cited by this paper
• Conditional Image Generation with PixelCNN Decoders

  2016cited by this paper
• The Variational Gaussian Process

  2015cited by this paper
• Generating Sentences from a Continuous Space

  2015cited by this paper
• MADE: Masked Autoencoder for Distribution Estimation

  2015influential reference
• Variational Inference with Normalizing Flows

  2015influential reference
• Efficient Gradient-Based Inference through Transformations between Bayes Nets and Neural Nets

  2014cited by this paper
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models

  2014influential reference
• Amortized Inference in Probabilistic Reasoning

  2014cited by this paper
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap

  2014cited by this paper
• NICE: Non-linear Independent Components Estimation

  2014cited by this paper
• A Family of Nonparametric Density Estimation Algorithms

  2013cited by this paper
• Stochastic variational inference

  2012cited by this paper
• DENSITY ESTIMATION BY DUAL ASCENT OF THE LOG-LIKELIHOOD ∗

  2010cited by this paper
• An Introduction to Variational Methods for Graphical Models

  1999cited by this paper
• On orthogonal block elimination

  1996cited by this paper
• A Basis-Kernel Representation of Orthogonal Matrices

  1995cited by this paper
• An Iterative Algorithm for Computing the Best Estimate of an Orthogonal Matrix

  1971cited by this paper
• Some Iterative Methods for Improving Orthonormality

  1970cited by this paper

• Adaptive Heterogeneous Mixtures of Normalising Flows for Robust Variational Inference

  2025cites this paper
• Data augmentation for forecasting industrial aging processes via conditional multimodal generative time-series models

  2025cites this paper
• Deep Sylvester Posterior Inference for Adaptive Compressed Sensing in Ultrasound Imaging

  2025cites this paper
• Score-Debiased Kernel Density Estimation

  2025cites this paper
• Physics-Informed Sylvester Normalizing Flows for Bayesian Inference in Magnetic Resonance Spectroscopy

  2025cites this paper
• An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures

  2025cites this paper
• Generative Artificial Intelligence for Internet of Things Computing: A Systematic Survey

  2025cites this paper
• Multi-Energy Quasi-Symplectic Langevin Inference for Latent Disentangled Learning

  2025cites this paper
• Asymptotically exact variational flows via involutive MCMC kernels

  2025cites this paper
• LLM-Prior: A Framework for Knowledge-Driven Prior Elicitation and Aggregation

  2025cites this paper
• Discrete-Time Maximum Likelihood Neural Distribution Steering

  2024cites this paper
• Smoothed Robustness Analysis: Bridging worst- and average-case robustness analyses via smoothed analysis

  2024cites this paper
• Empirical evaluation of normalizing flows in Markov chain Monte Carlo

  2024cites this paper
• Physics-integrated generative modeling using attentive planar normalizing flow based variational autoencoder

  2024cites this paper
• PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise

  2024cites this paper
• Probabilistic Forecasting of Irregular Time Series via Conditional Flows

  2024cites this paper
• Variational Bayesian Optimal Experimental Design with Normalizing Flows

  2024cites this paper
• Meta-Learning Universal Priors Using Non-Injective Change of Variables

  2024influential citation
• Shape embedding and retrieval in multi-flow deformation

  2024cites this paper
• Generating Dual-Arm Inverse Kinematics Solutions using Latent Variable Models

  2024cites this paper
• Model-agnostic search for dijet resonances with anomalous jet substructure in proton–proton collisions at s = 13 TeV

  2024cites this paper
• Parallelizing Linear Transformers with the Delta Rule over Sequence Length

  2024cites this paper
• Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models

  2024cites this paper
• EigenVI: score-based variational inference with orthogonal function expansions

  2024cites this paper
• ExpM+NF: Differentially Private Machine Learning that Surpasses DPSGD

  2023cites this paper
• Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model

  2023cites this paper
• Are Normalizing Flows the Key to Unlocking the Exponential Mechanism?

  2023cites this paper
• Conditional invertible image re-scaling

  2023cites this paper
• Deep generative models for detector signature simulation: A taxonomic review

  2023cites this paper
• Fast posterior probability sampling with normalizing flows and its applicability in Bayesian analysis in particle physics

  2023cites this paper
• AIGC for Various Data Modalities: A Survey

  2023cites this paper
• Infrared image super-resolution reconstruction based on high-frequency prior convolutional neural network

  2023cites this paper
• Deep Generative Models for Detector Signature Simulation: An Analytical Taxonomy

  2023cites this paper
• One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models

  2023cites this paper
• Multi-way Variational NMT for UGC: Improving Robustness in Zero-shot Scenarios via Mixture Density Networks

  2023cites this paper
• GC-Flow: A Graph-Based Flow Network for Effective Clustering

  2023cites this paper
• Explicitly Minimizing the Blur Error of Variational Autoencoders

  2023cites this paper
• Boosting Summarization with Normalizing Flows and Aggressive Training

  2023influential citation
• Geometric Clifford Algebra Networks

  2023cites this paper
• Embracing the chaos: analysis and diagnosis of numerical instability in variational flows

  2023cites this paper
• Probabilistic 3D segmentation for aleatoric uncertainty quantification in full 3D medical data

  2023influential citation
• Isomorphism, Normalizing Flows, and Density Estimation: Preserving Relationships Between Data

  2023cites this paper
• Hierarchical Disentangled Representation for Invertible Image Denoising and Beyond

  2023cites this paper
• Conditional Matrix Flows for Gaussian Graphical Models

  2023cites this paper
• Disentangling Style and Speaker Attributes for TTS Style Transfer

  2022cites this paper
• Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesis

  2022cites this paper
• Solving Fokker–Planck equations using deep KD-tree with a small amount of data

  2022cites this paper
• Universality of parametric Coupling Flows over parametric diffeomorphisms

  2022cites this paper
• Langevin Autoencoders for Learning Deep Latent Variable Models

  2022cites this paper
• Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework

  2022cites this paper
• Bernstein flows for flexible posteriors in variational Bayes

  2022cites this paper
• Para-CFlows: $C^k$-universal diffeomorphism approximators as superior neural surrogates

  2022cites this paper
• Causal Effect Prediction with Flow-based Inference

  2022cites this paper
• Sparse Approximation of Triangular Transports, Part I: The Finite-Dimensional Case

  2022cites this paper
• Generalized Product-of-Experts for Learning Multimodal Representations in Noisy Environments

  2022cites this paper
• Normalizing Flows for Hierarchical Bayesian Analysis: A Gravitational Wave Population Study

  2022cites this paper
• Fast Computer Model Calibration using Annealed and Transformed Variational Inference

  2022cites this paper
• Invertible Rescaling Network and Its Extensions

  2022cites this paper
• CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations

  2022cites this paper
• DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents

  2022cites this paper
• Variational Flow Graphical Model

  2022influential citation
• Anomalous Trajectory Detection Using Masked Autoregressive Flow Considering Route Choice Probability

  2022cites this paper
• TAP: Traffic Accident Profiling via Multi-Task Spatio-Temporal Graph Representation Learning

  2022cites this paper
• Flow-Based Fast Multichannel Nonnegative Matrix Factorization for Blind Source Separation

  2022cites this paper
• Flow-based Recurrent Belief State Learning for POMDPs

  2022cites this paper
• A Linearly Convergent Douglas-Rachford Splitting Solver for Markovian Information-Theoretic Optimization Problems

  2022cites this paper
• Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification

  2022influential citation
• Amortized Variational Inference with Gaussian Mixture Models

  2022cites this paper
• Statistical Model Criticism of Variational Auto-Encoders

  2022cites this paper
• Principal Manifold Flows

  2022cites this paper
• Path-Gradient Estimators for Continuous Normalizing Flows

  2022cites this paper
• Principal Component Flows

  2022cites this paper
• Profiling Users for Question Answering Communities via Flow-Based Constrained Co-Embedding Model

  2021cites this paper
• A Dynamical System Perspective for Lipschitz Neural Networks

  2021cites this paper
• ELF: Exact-Lipschitz Based Universal Density Approximator Flow

  2021cites this paper
• Conditional Invertible Neural Networks for Medical Imaging

  2021cites this paper
• Sinusoidal Flow: A Fast Invertible Autoregressive Flow

  2021cites this paper
• Bootstrap Your Flow

  2021cites this paper
• General Hypernetwork Framework for Creating 3D Point Clouds

  2021cites this paper
• Neural Flows: Efficient Alternative to Neural ODEs

  2021influential citation
• MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining

  2021influential citation
• Viscos Flows: Variational Schur Conditional Sampling With Normalizing Flows

  2021cites this paper
• Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows

  2021influential citation
• Modeling Item Response Theory with Stochastic Variational Inference

  2021cites this paper
• Scalable Lipschitz Residual Networks with Convex Potential Flows

  2021cites this paper
• Challenges for unsupervised anomaly detection in particle physics

  2021cites this paper
• Generalization of the Change of Variables Formula with Applications to Residual Flows

  2021cites this paper
• On the Generative Utility of Cyclic Conditionals

  2021influential citation
• Sparse Flows: Pruning Continuous-depth Models

  2021cites this paper
• Implicit Variational Conditional Sampling with Normalizing Flows

  2021cites this paper
• Decoupling Global and Local Representations via Invertible Generative Flows

  2021cites this paper
• Distilling the Knowledge from Normalizing Flows

  2021cites this paper
• Model Selection for Bayesian Autoencoders

  2021cites this paper
• PU-Flow: A Point Cloud Upsampling Network With Normalizing Flows

  2021cites this paper
• Learning Flexibly Distributional Representation for Low-quality 3D Face Recognition

  2021cites this paper
• Augmented KRnet for density estimation and approximation

  2021cites this paper
• Structured Dropout Variational Inference for Bayesian Neural Networks

  2021cites this paper
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider

  2021influential citation
• Improving Aleatoric Uncertainty Quantification in Multi-Annotated Medical ImageSegmentation with Normalizing Flows

  2021cites this paper
• Universal Approximation of Residual Flows in Maximum Mean Discrepancy

  2021cites this paper