awesome-normalizing-flows
Awesome resources on normalizing flows.
https://github.com/janosh/awesome-normalizing-flows
Last synced: 27 days ago
JSON representation
🛠️ Applications <small>(8)</small>
- Normalizing Kalman Filters for Multivariate Time Series Analysis
- Amazon Science
- On the Sentence Embeddings from Pre-trained Language Models
- Targeted free energy estimation via learned mappings
- Faster Uncertainty Quantification for Inverse Problems with Conditional Normalizing Flows
- [Video
- SRFlow: Learning the Super-Resolution Space with Normalizing Flow
- NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
- Analyzing Inverse Problems with Invertible Neural Networks
- Latent Space Policies for Hierarchical Reinforcement Learning
- Targeted free energy estimation via learned mappings
- [Video
- On the Sentence Embeddings from Pre-trained Language Models
- [Video
- Amazon Science
🌐 Blog Posts <small>(5)</small>
<img src="assets/other.svg" alt="Other" height="20px"> Other Repos
🚧 Contributing
<img src="assets/other.svg" alt="Other" height="20px"> Other Repos
📦 Packages <small>(13)</small>
<img src="assets/pytorch.svg" alt="PyTorch" height="20px"> PyTorch Packages
📦 Packages <small>(14)</small>
<img src="assets/jax.svg" alt="JAX" height="20px"> JAX Packages
<img src="assets/julia.svg" alt="Julia" height="20px"> Julia Packages
<img src="assets/pytorch.svg" alt="PyTorch" height="20px"> PyTorch Packages
📦 Packages <small>(15)</small>
<img src="assets/jax.svg" alt="JAX" height="20px"> JAX Packages
<img src="assets/julia.svg" alt="Julia" height="20px"> Julia Packages
<img src="assets/pytorch.svg" alt="PyTorch" height="20px"> PyTorch Packages
- Jammy Flows
- flowtorch
- nflows
- normflows
- LAMPE - free AMortized Posterior Estimation with PyTorch.
- FrEIA - heidelberg.de/vislearn)
<img src="assets/tensorflow.svg" alt="TensorFlow" height="20px"> TensorFlow Packages
📝 Publications <small>(57)</small>
📝 Publications <small>(60)</small>
- FInC Flow: Fast and Invertible k×k Convolutions for Normalizing Flows
- Invertible Monotone Operators for Normalizing Flows
- ManiFlow: Implicitly Representing Manifolds with Normalizing Flows
- Graphical Normalizing Flows
- Multi-scale Attention Flow for Probabilistic Time Series Forecasting
- E(n) Equivariant Normalizing Flows
- CInC Flow: Characterizable Invertible 3x3 Convolution
- Orthogonalizing Convolutional Layers with the Cayley Transform
- Improving Normalizing Flows via Better Orthogonal Parameterizations - Casado et al.
- Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows
- [OpenReview.net - ts)]
- Haar Wavelet based Block Autoregressive Flows for Trajectories
- AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
- SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
- Why Normalizing Flows Fail to Detect Out-of-Distribution Data
- [Tweet
- Equivariant Flows: exact likelihood generative learning for symmetric densities
- The Convolution Exponential and Generalized Sylvester Flows
- iUNets: Fully invertible U-Nets with Learnable Upand Downsampling
- Normalizing Flows with Multi-Scale Autoregressive Priors
- Flows for simultaneous manifold learning and density estimation
- [Tweet - flow)]
- Gaussianization Flows
- Gradient Boosted Normalizing Flows
- Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows
- [Tweet
- Stochastic Normalizing Flows
- Stochastic Normalizing Flows (SNF)
- [Tweet
- Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
- Invertible Generative Modeling using Linear Rational Splines
- Normalizing Flows for Probabilistic Modeling and Inference
- Unconstrained Monotonic Neural Networks
- Normalizing Flows: An Introduction and Review of Current Methods
- Noise Regularization for Conditional Density Estimation
- [Blog
- MintNet: Building Invertible Neural Networks with Masked Convolutions
- Densely connected normalizing flows
- Invertible Convolutional Flow
- Invertible Convolutional Networks
- Neural Spline Flows
- Graph Normalizing Flows
- Fast Flow Reconstruction via Robust Invertible n x n Convolution
- Integer Discrete Flows and Lossless Compression
- Block Neural Autoregressive Flow
- MaCow: Masked Convolutional Generative Flow
- Emerging Convolutions for Generative Normalizing Flows
- FloWaveNet : A Generative Flow for Raw Audio
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- Glow: Generative Flow with Invertible 1x1 Convolutions
- Neural Autoregressive Flows
- Sylvester Normalizing Flow for Variational Inference
- Convolutional Normalizing Flows
- Masked Autoregressive Flow for Density Estimation
- Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
- Improving Variational Inference with Inverse Autoregressive Flow
- Density estimation using Real NVP - Dickstein et al.
- Variational Inference with Normalizing Flows
- Masked Autoencoder for Distribution Estimation
- Non-linear Independent Components Estimation
- Iterative Gaussianization: from ICA to Random Rotations - Valls et al.
- Transferable Boltzmann Generators
- [Code
- Adaptive Monte Carlo augmented with normalizing flows
- [Code
- Efficient Bayesian Sampling Using Normalizing Flows to Assist Markov Chain Monte Carlo Methods
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- [Code
- Adaptive Monte Carlo augmented with normalizing flows
- [Video
- [Tweet - flow)]
- [Video
🧑💻 Repos <small>(18)</small>
<img src="assets/jax.svg" alt="JAX" height="20px"> JAX Repos
<img src="assets/other.svg" alt="Other" height="20px"> Other Repos
- Deep Density Destructors - based as well as Gaussianization methods which are similar to normalizing flows except they converge iteratively instead of fully parametrized. That is, they still use bijective transforms, compute the Jacobian, check the likelihood and you can still sample and get probability density estimates. The only difference is you repeat the following two steps until convergence:
- Normalizing Flows Overview
- Normalizing Flows Overview
- Destructive Deep Learning (ddl)
- Theano
- NormFlows
- `autograd` - level.
<img src="assets/pytorch.svg" alt="PyTorch" height="20px"> PyTorch Repos
- NICE: Non-linear Independent Components Estimation
- Normalizing Flows - Introduction (Part 1)
- Parts 2 and 3 coming later
- Density Estimation with Neural ODEs and Density Estimation with FFJORDs
- Graphical Normalizing Flows
- Unconstrained Monotonic Neural Networks (UMNN)
- DeeProb-kit
- StyleFlow
- [Docs
- pytorch-normalizing-flows
- pytorch_flows - ircam](https://github.com/acids-ircam)
- normalizing_flows
- pytorch-flows
- Density Estimation with Neural ODEs and Density Estimation with FFJORDs
<img src="assets/tensorflow.svg" alt="TensorFlow" height="20px"> TensorFlow Repos
📺 Videos <small>(8)</small>
- Normalizing Flows - Motivations, The Big Idea & Essential Foundations
- Normalizing Flows - book.github.io/slopes-expectations.html)
- full series
- Introduction to Normalizing Flows
- Flow Models - cs294-158-sp20/home)
- What are normalizing flows?
- A primer on normalizing flows - dinh.github.io)
- Graph Normalizing Flows
- Sylvester Normalizing Flow for Variational Inference
- What are normalizing flows?
- A primer on normalizing flows - dinh.github.io)
- Graph Normalizing Flows
- Sylvester Normalizing Flow for Variational Inference
- Normalizing Flows - Motivations, The Big Idea & Essential Foundations
- Normalizing Flows - book.github.io/slopes-expectations.html)
- Introduction to Normalizing Flows
- Flow Models - cs294-158-sp20/home)
- full series
- What are normalizing flows?
- A primer on normalizing flows - dinh.github.io)
- Graph Normalizing Flows
- Sylvester Normalizing Flow for Variational Inference
- Normalizing Flows - Motivations, The Big Idea & Essential Foundations
- Normalizing Flows - book.github.io/slopes-expectations.html)
- Introduction to Normalizing Flows
- Flow Models - cs294-158-sp20/home)