Normalizing Flows: An Introduction and Review of Current Methods

Abstract

Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature around the construction and use of Normalizing Flows for distribution learning. We aim to provide context and explanation of the models, review current state-of-the-art literature, and identify open questions and promising future directions.

arXiv commentThis paper appears in: IEEE Transactions on Pattern Analysis and Machine Intelligence On page(s): 1-16 Print ISSN: 0162-8828 Online ISSN: 0162-8828

References in corpus (53)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Auto-Encoding Variational Bayes
• Generative Adversarial Networks: An Overview
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• NICE: Non-linear Independent Components Estimation
• Variational Inference with Normalizing Flows
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Normalizing Flows for Probabilistic Modeling and Inference
• Parallel WaveNet: Fast High-Fidelity Speech Synthesis
• MADE: Masked Autoencoder for Distribution Estimation
• Equivariant flow-based sampling for lattice gauge theory
• The Reversible Residual Network: Backpropagation Without Storing Activations
• Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
• Residual Flows for Invertible Generative Modeling
• Invertible Residual Networks
• Scalable Gradients for Stochastic Differential Equations
• Sylvester Normalizing Flows for Variational Inference
• How to train your neural ODE: the world of Jacobian and kinetic regularization
• GraphNVP: An Invertible Flow Model for Generating Molecular Graphs
• AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
• Improving Variational Auto-Encoders using Householder Flow
• Normalizing Flows on Tori and Spheres
• Targeted free energy estimation via learned mappings
• Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models
• High-Dimensional Probability Estimation with Deep Density Models
• Pathwise Derivatives Beyond the Reparameterization Trick
• Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
• Latent Normalizing Flows for Discrete Sequences
• Normalizing Flows on Riemannian Manifolds
• Equivariant Flows: sampling configurations for multi-body systems with symmetric energies
• Emerging Convolutions for Generative Normalizing Flows
• Gravitational wave population inference with deep flow-based generative network
• Discrete Flows: Invertible Generative Models of Discrete Data
• Sum-of-Squares Polynomial Flow
• Conditional Density Estimation with Bayesian Normalising Flows
• Universal audio synthesizer control with normalizing flows
• Continuous-Time Flows for Efficient Inference and Density Estimation
• Approximation Capabilities of Neural ODEs and Invertible Residual Networks
• Learning across scales - A multiscale method for Convolution Neural Networks
• Poincaré Wasserstein Autoencoder
• Semi-Conditional Normalizing Flows for Semi-Supervised Learning
• A RAD approach to deep mixture models
• Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow
• Learning Discrete Distributions by Dequantization
• Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies
• Convolutional Normalizing Flows
• Deep Diffeomorphic Normalizing Flows
• Unconstrained Monotonic Neural Networks
• Latent Variable Modelling with Hyperbolic Normalizing Flows
• Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling
• Likelihood Contribution based Multi-scale Architecture for Generative Flows
• Infinitely deep neural networks as diffusion processes

Cited by in corpus (288)

• A Unifying Review of Deep and Shallow Anomaly Detection
• Normalizing Flows for Probabilistic Modeling and Inference
• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• On the use of Artificial Neural Networks in Topology Optimisation
• Deep Learning in Deterministic Computational Mechanics
• Nested Sampling with Normalising Flows for Gravitational-Wave Inference
• StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
• At the Dawn of Generative AI Era: A Tutorial-cum-Survey on New Frontiers in 6G Wireless Intelligence
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Learning Disentangled Representations in the Imaging Domain
• A Comprehensive Review of Data-Driven Co-Speech Gesture Generation
• Invertible Networks or Partons to Detector and Back Again
• AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity
• On the Quantum versus Classical Learnability of Discrete Distributions
• Understanding Event-Generation Networks via Uncertainties
• Accelerating Monte Carlo event generation -- rejection sampling using neural network event-weight estimates
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
• GANplifying Event Samples
• Generative Networks for Precision Enthusiasts
• Non-Gaussian estimates of tensions in cosmological parameters
• Generative AI and Process Systems Engineering: The Next Frontier
• Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
• Normalizing field flows: Solving forward and inverse stochastic differential equations using physics-informed flow models
• Denoising Diffusion Post-Processing for Low-Light Image Enhancement
• Targeting Multi-Loop Integrals with Neural Networks
• Phase Space Sampling and Inference from Weighted Events with Autoregressive Flows
• CURTAINs for your Sliding Window: Constructing Unobserved Regions by Transforming Adjacent Intervals
• The Gaussian equivalence of generative models for learning with shallow neural networks
• Presenting Unbinned Differential Cross Section Results
• Importance nested sampling with normalising flows
• Normalizing flows for atomic solids
• FETA: Flow-Enhanced Transportation for Anomaly Detection
• Stochastic normalizing flows as non-equilibrium transformations
• DCTRGAN: Improving the Precision of Generative Models with Reweighting
• Digital staining in optical microscopy using deep learning -- a review
• Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows
• Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion
• normflows: A PyTorch Package for Normalizing Flows
• Normalizing flows as an avenue to study overlapping gravitational wave signals
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Evidence for eccentricity in the population of binary black holes observed by LIGO-Virgo-KAGRA
• Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
• Measuring QCD Splittings with Invertible Networks
• Inference of cosmic-ray source properties by conditional invertible neural networks
• Translating neutron star observations to nuclear symmetry energy via artificial neural networks
• Path integral contour deformations for observables in $SU(N)$ gauge theory
• Deep Learning-Based Super-Resolution and De-Noising for XMM-Newton Images
• Galaxy Clustering Analysis with SimBIG and the Wavelet Scattering Transform
• Deep Unfolding with Normalizing Flow Priors for Inverse Problems
• SymmetryGAN: Symmetry Discovery with Deep Learning
• On the representation and learning of monotone triangular transport maps
• Euclid preparation: XIII. Forecasts for galaxy morphology with the Euclid Survey using Deep Generative Models
• Inductive Simulation of Calorimeter Showers with Normalizing Flows
• Towards a Deep Learning Model for Hadronization
• Dim but not entirely dark: Extracting the Galactic Center Excess' source-count distribution with neural nets
• Bayesian Stokes inversion with Normalizing flows
• CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows
• A Flow-Based Neural Network for Time Domain Speech Enhancement
• Gravitational wave populations and cosmology with neural posterior estimation
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
• Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence
• CaloFlow for CaloChallenge Dataset 1
• Koopman operator learning using invertible neural networks
• Anomaly Detection under Coordinate Transformations
• Mapping Dark Matter in the Milky Way using Normalizing Flows and Gaia DR3
• Creativity in the era of artificial intelligence
• On the Sentence Embeddings from Pre-trained Language Models
• Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model
• Perfect density models cannot guarantee anomaly detection
• High-dimensional and Permutation Invariant Anomaly Detection
• Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
• Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech
• Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstruction
• Learning the temporal evolution of multivariate densities via normalizing flows
• Recent advances in deep learning theory
• Unsupervised in-distribution anomaly detection of new physics through conditional density estimation
• Probabilistic Forward Modeling of Galaxy Catalogs with Normalizing Flows
• Learning Likelihood Ratios with Neural Network Classifiers
• Ephemeral Learning -- Augmenting Triggers with Online-Trained Normalizing Flows
• Conditional score-based diffusion models for solving inverse problems in mechanics
• AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
• Wavelet Flow: Fast Training of High Resolution Normalizing Flows
• ELSA -- Enhanced latent spaces for improved collider simulations
• Advancing Space-Based Gravitational Wave Astronomy: Rapid Parameter Estimation via Normalizing Flows
• Free energy calculation of crystalline solids using normalizing flow
• Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
• A survey of machine learning-based physics event generation
• Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows
• Hypersolvers: Toward Fast Continuous-Depth Models
• Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
• Charting Galactic Accelerations: When and How to Extract a Unique Potential from the Distribution Function
• Variational Inference with NoFAS: Normalizing Flow with Adaptive Surrogate for Computationally Expensive Models
• Bridging Mean-Field Games and Normalizing Flows with Trajectory Regularization
• Solving multiphysics-based inverse problems with learned surrogates and constraints
• Exploring the evolution of gravitational-wave emitters with efficient emulation: Constraining the origins of binary black holes using normalising flows
• L-HYDRA: Multi-Head Physics-Informed Neural Networks
• Online Neural Path Guiding with Normalized Anisotropic Spherical Gaussians
• Variational Prior Replacement in Bayesian Inference and Inversion
• Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows
• Differentiable MadNIS-Lite
• Measuring Galactic Dark Matter through Unsupervised Machine Learning
• Variational inference of fractional Brownian motion with linear computational complexity
• Variational Bayesian Optimal Experimental Design with Normalizing Flows
• Convergence of flow-based generative models via proximal gradient descent in Wasserstein space
• Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN
• Bayesian evidence-driven diagnosis of instrumental systematics for sky-averaged 21-cm cosmology experiments
• PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction
• Detecting dense-matter phase transition signatures in neutron star mass-radius measurements as data anomalies using normalising flows
• EPR-Net: Constructing non-equilibrium potential landscape via a variational force projection formulation
• Efficient Rare Event Sampling with Unsupervised Normalising Flows
• Towards a data-driven model of hadronization using normalizing flows
• Graphical Normalizing Flows
• Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization
• SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series Imputation
• Modeling Extremal Streamflow using Deep Learning Approximations and a Flexible Spatial Process
• Decoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of State
• Parameterized quantum circuits as universal generative models for continuous multivariate distributions
• Learning Many-to-Many Mapping for Unpaired Real-World Image Super-resolution and Downscaling
• PredDiff: Explanations and Interactions from Conditional Expectations
• Rapid inference and comparison of gravitational-wave population models with neural variational posteriors
• Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
• Hyperbolic Deep Neural Networks: A Survey
• Data-driven Estimation of Background Distribution through Neural Autoregressive Flows
• End-to-End Modeling Hierarchical Time Series Using Autoregressive Transformer and Conditional Normalizing Flow based Reconciliation
• Latent Variable Modelling with Hyperbolic Normalizing Flows
• Emerging Directions in Geophysical Inversion
• Automatic structured variational inference
• Creating New Voices using Normalizing Flows
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Comparison of Affine and Rational Quadratic Spline Coupling and Autoregressive Flows through Robust Statistical Tests
• Disentangling Geometric Deformation Spaces in Generative Latent Shape Models
• Active inference and deep generative modeling for cognitive ultrasound
• Deep Generative Modeling-based Data Augmentation with Demonstration using the BFBT Benchmark Void Fraction Datasets
• Utilizing variational autoencoders in the Bayesian inverse problem of photoacoustic tomography
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• OverFlow: Putting flows on top of neural transducers for better TTS
• Hyperbolic Secant representation of the logistic function: Application to probabilistic Multiple Instance Learning for CT intracranial hemorrhage detection
• Parameterizing pressure-temperature profiles of exoplanet atmospheres with neural networks
• Multiscale Representation Enhanced Temporal Flow Fusion Model for Long-Term Workload Forecasting
• CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation
• Functional Autoencoder for Smoothing and Representation Learning
• Flow Matching for Atmospheric Retrieval of Exoplanets: Where Reliability meets Adaptive Noise Levels
• StarFlow: Leveraging Normalizing Flows for Stellar Age Estimation in SDSS-V DR19
• Towards Empirical Sandwich Bounds on the Rate-Distortion Function
• Intact-VAE: Estimating Treatment Effects under Unobserved Confounding
• Sequential Neural Posterior and Likelihood Approximation
• Generative Adversarial Networks for Scintillation Signal Simulation in EXO-200
• Posterior Estimation Using Deep Learning: A Simulation Study of Compartmental Modeling in Dynamic PET
• What does a cosmological experiment really measure? Covariant posterior decomposition with normalizing flows
• Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms
• Emission Line Predictions for Mock Galaxy Catalogues: a New Differentiable and Empirical Mapping from DESI
• Unsupervised and lightly supervised learning in particle physics
• Sensing Anomalies as Potential Hazards: Datasets and Benchmarks
• Training normalizing flows with computationally intensive target probability distributions
• Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders
• Learning to solve Bayesian inverse problems: An amortized variational inference approach using Gaussian and Flow guides
• Watch and learn -- a generalized approach for transferrable learning in deep neural networks via physical principles
• GalaxyFlow: Upsampling Hydrodynamical Simulations for Realistic Mock Stellar Catalogs
• Variational Sequential Optimal Experimental Design using Reinforcement Learning
• A deep-learning approach to the 3D reconstruction of dust density and temperature in star-forming regions
• Pseudo-Rehearsal for Continual Learning with Normalizing Flows
• How to GAN Event Unweighting
• Isolating Unisolated Upsilons with Anomaly Detection in CMS Open Data
• Fast and accurate parameter estimation of high-redshift sources with the Einstein Telescope
• TopicFlow: Disentangling quark and gluon jets with normalizing flows
• InFlow: Robust outlier detection utilizing Normalizing Flows
• Bayesian nonparametric generative modeling of large multivariate non-Gaussian spatial fields
• MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference
• Simulation-based inference of single-molecule force spectroscopy
• Deep Conditional Transformation Models
• Equation-of-state-informed pulse profile modeling
• UFO-BLO: Unbiased First-Order Bilevel Optimization
• Simulation-Based Inference of Surface Accumulation and Basal Melt Rates of an Antarctic Ice Shelf from Isochronal Layers
• Temperature-steerable flows
• Calibrated Multiple-Output Quantile Regression with Representation Learning
• A Neural Network MCMC sampler that maximizes Proposal Entropy
• Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow
• $H_0$ Without the Sound Horizon (or Supernovae): A 2% Measurement in DESI DR1
• Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability
• Testing the boundaries: Normalizing Flows for higher dimensional data sets
• Semi-supervised Learning with Missing Values Imputation
• Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks
• Relative gradient optimization of the Jacobian term in unsupervised deep learning
• Speed-accuracy relations for diffusion models: Wisdom from nonequilibrium thermodynamics and optimal transport
• Calibrating multi-dimensional complex ODE from noisy data via deep neural networks
• PETRA: From the LISA global fit to a catalog of Galactic binaries
• Identifying through Flows for Recovering Latent Representations
• Point Process Flows
• Sum-Product-Transform Networks: Exploiting Symmetries using Invertible Transformations
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
• BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning
• Contrastive Unpaired Translation using Focal Loss for Patch Classification
• Marginalizable Density Models
• LHC Hadronic Jet Generation Using Convolutional Variational Autoencoders with Normalizing Flows
• Top-philic Machine Learning
• Deciphering Baryonic Feedback from ACT tSZ Galaxy Clusters
• Joint inference for gravitational wave signals and glitches using a data-informed glitch model
• Toward a foundation model for heavy-ion collision experiments based on point-cloud diffusion
• Detecting the third family of compact stars with normalizing flows
• Generative modeling of time-dependent densities via optimal transport and projection pursuit
• A Mathematical Framework for Learning Probability Distributions
• Robust normalizing flows using Bernstein-type polynomials
• Unifying supervised learning and VAEs -- coverage, systematics and goodness-of-fit in normalizing-flow based neural network models for astro-particle reconstructions
• Flow-based Nonperturbative Simulation of First-order Phase Transitions
• Parameterized Wasserstein Gradient Flow
• Expert-Guided Symmetry Detection in Markov Decision Processes
• Extracting overlapping gravitational-wave signals of galactic compact binaries: a mini review
• Jacobian Determinant of Normalizing Flows
• Learning Dynamics Models with Stable Invariant Sets
• Leveraging Normalizing Flows for Orbital-Free Density Functional Theory
• Latent Space Refinement for Deep Generative Models
• Rectangular Flows for Manifold Learning
• Unconstrained Monotonic Calibration of Predictions in Deep Ranking Systems
• Minimal Autocorrelation in Hybrid Monte Carlo simulations using Exact Fourier Acceleration
• Learning Informed Prior Distributions with Normalizing Flows for Bayesian Analysis
• A continuous calibration of the ATLAS flavour-tagging classifiers via optimal transportation maps
• Data Augmentation through Expert-guided Symmetry Detection to Improve Performance in Offline Reinforcement Learning
• Event Generation and Density Estimation with Surjective Normalizing Flows
• Overcoming the Limitations of Localization Uncertainty: Efficient & Exact Non-Linear Post-Processing and Calibration
• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration
• A Blob Method for Mean Field Control With Terminal Constraints
• Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows
• Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling
• Reconstructing Interpretable Features in Computational Super-Resolution microscopy via Regularized Latent Search
• State-observation augmented diffusion model for nonlinear assimilation with unknown dynamics
• Density Estimation via Binless Multidimensional Integration
• Local Surface Parameterizations via Smoothed Geodesic Splines
• Physically Interpretable Probabilistic Domain Characterization
• Avoiding subtraction and division of stochastic signals using normalizing flows: NFdeconvolve
• Data-Driven High-Dimensional Statistical Inference with Generative Models
• Generative flow-based warm start of the variational quantum eigensolver
• Mitigating Model Misspecification in Simulation-Based Inference for Galaxy Clustering
• A normalizing flow approach for the inference of star cluster properties from unresolved broadband photometry I: Comparison to spectral energy distribution fitting
• Manifold Density Estimation via Generalized Dequantization
• Comparing next-generation detector configurations for high-redshift gravitational wave sources with neural posterior estimation
• Motion Mappings for Continuous Bilateral Teleoperation
• Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities
• Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users
• Spectral classification of young stars using conditional invertible neural networks II. Application to Trumpler 14 in Carina
• Monte Carlo guided Diffusion for Bayesian linear inverse problems
• Quasi-symplectic Langevin Variational Autoencoder
• Learning Optimal Transport Between two Empirical Distributions with Normalizing Flows
• ANFIC: Image Compression Using Augmented Normalizing Flows
• Copula-Based Normalizing Flows
• Neural density estimation and uncertainty quantification for laser induced breakdown spectroscopy spectra
• Causal Autoregressive Flows
• Differentiate Everything with a Reversible Embeded Domain-Specific Language
• Global sampling of Feynman's diagrams through Normalizing Flow
• Generalization of the Change of Variables Formula with Applications to Residual Flows
• Data-Driven Predictions for Dark Photon and Millicharged Particle Production
• Comparing Dynamical Models Through Diffeomorphic Vector Field Alignment
• A method to derive self-consistent NLTE astrophysical parameters for 4 million high-resolution 4MOST stellar spectra in half a day with invertible neural networks
• Weighting-Based Treatment Effect Estimation via Distribution Learning
• Generative Adversarial Learning via Kernel Density Discrimination
• Sampling the Liquid-Gas Critical Point with Boltzmann Generators
• Time-changed normalizing flows for accurate SDE modeling
• Abelian Neural Networks
• Contrastive Representations for Label Noise Require Fine-Tuning
• Improving the expressiveness of neural vocoding with non-affine Normalizing Flows
• Uncertainty quantification for ptychography using normalizing flows
• Delta-GAN-Encoder: Encoding Semantic Changes for Explicit Image Editing, using Few Synthetic Samples
• Minimax Analysis for Inverse Risk in Nonparametric Planer Invertible Regression
• Counterfactual Explanations via Latent Space Projection and Interpolation
• Charting galactic accelerations II: how to 'learn' accelerations in the solar neighbourhood
• A Triangular Network For Density Estimation
• Transformation Models for Flexible Posteriors in Variational Bayes
• Continuous Latent Process Flows
• Equivariant Manifold Flows
• Entropic Issues in Likelihood-Based OOD Detection
• Learning and Generalization in Overparameterized Normalizing Flows
• NeuMC -- a package for neural sampling for lattice field theories
• Invertible Attention
• Generative Actor-Critic: An Off-policy Algorithm Using the Push-forward Model
• On the performance of multi-fidelity and reduced-dimensional neural emulators for inference of physiological boundary conditions
• Overcoming barriers to scalability in variational quantum Monte Carlo
• Conjunction Data Messages behave as a Poisson Process
• Statistical model-based evaluation of neural networks
• Lightweight posterior construction for gravitational-wave catalogs with the Kolmogorov-Arnold network
• Semantic and Geometric Unfolding of StyleGAN Latent Space
• Physics Informed Convex Artificial Neural Networks (PICANNs) for Optimal Transport based Density Estimation
• X2CT-FLOW: Maximum a posteriori reconstruction using a progressive flow-based deep generative model for ultra sparse-view computed tomography in ultra low-dose protocols
• Exploring the Early Universe with Deep Learning
• Continuous normalizing flows on manifolds
• ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models
• Neural Canonical Transformation for the Spectra of Fluxional Molecule CH5+
• Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi^4 field theory
• Learning to Shift Attention for Motion Generation