methodology-9

Normalising Flows

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in normalising-flows-9

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find normalising-flows-9 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Block Neural Autoregressive Flow

Nicola De Cao, Ivan Titov, Wilker Aziz•Mon Apr 08 2019

Normalising flows (NFS) map two density functions via a differentiable bijection whose Jacobian determinant can be computed efficiently. Recently, as an alternative to hand-crafted bijections, Huang et al. (2018) proposed neural autoregressive flow (NAF) which is a universal approximator for density functions. Their flow is a neural network (NN) whose parameters are predicted by another NN. The latter grows quadratically with the size of the former and thus an efficient technique for parametrization is needed. We propose block neural autoregressive flow (B-NAF), a much more compact universal approximator of density functions, where we model a bijection directly using a single feed-forward network. Invertibility is ensured by carefully designing each affine transformation with block matrices that make the flow autoregressive and (strictly) monotone. We compare B-NAF to NAF and other established flows on density estimation and approximate inference for latent variable models. Our proposed flow is competitive across datasets while using orders of magnitude fewer parameters.

Content

135 0

Paper Graph

Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows

A. Doucet, R. Cornish, Anthony L. Caterini, George Deligiannidis•Sun Sep 29 2019

It is proved that a flow must become arbitrarily numerically noninvertible in order to approximate the target closely, and proposed Continuously Indexed Flows (CIFs) are proposed, which replace the single bijection used by normalising flows with a continuously indexed family of bijections.

138 0

Paper Graph

Deep Structural Causal Models for Tractable Counterfactual Inference

Daniel Coelho de Castro, Nick Pawlowski, B. Glocker•Wed Jun 10 2020

The experimental results indicate that the proposed framework can successfully train deep SCMs that are capable of all three levels of Pearl's ladder of causation: association, intervention, and counterfactuals, giving rise to a powerful new approach for answering causal questions in imaging applications and beyond.

288 0

Paper Graph

Implicit Weight Uncertainty in Neural Networks

Ben Glocker, Nick Pawlowski, Martin Rajchl•Thu Nov 02 2017

The method, Bayes by Hypernet, is able to model a richer variational distribution than previous methods and achieves comparable predictive performance on the MNIST classification task while providing higher predictive uncertainties compared to MC-Dropout and regular maximum likelihood training.

98 0

Paper Graph

OverFlow: Putting flows on top of neural transducers for better TTS

G. Henter, J. Beskow, Shivam Mehta, Ambika Kirkland, Harm Lameris, Éva Székely•Sat Nov 12 2022

Experiments show that a system based on the proposed neural HMM TTS with normalising flows for describing the highly non-Gaussian distribution of speech acoustics needs fewer updates than comparable methods to produce accurate pronunciations and a subjective speech quality close to natural speech.

16 0

Paper Graph

The neural moving average model for scalable variational inference of state space models

Tom Ryder, D. Prangle, A. Golightly, Isaac Matthews•Tue Oct 01 2019

This work proposes an extension to state space models of time series data based on a novel generative model for latent temporal states: the neural moving average model, which permits a subsequence to be sampled without drawing from the entire distribution, enabling training iterations to use mini-batches of the time series at low computational cost.

8 0

Paper Graph

VFlow: More Expressive Generative Flows with Variational Data Augmentation

Jun Zhu, Cheng Lu, Jianfei Chen, Biqi Chenli, Tian Tian•Fri Feb 21 2020

VFlow achieves a new state-of-the-art 2.98 bits per dimension on the CIFAR-10 dataset and is more compact than previous models to reach similar modeling quality.

62 0

Paper Graph

Woodbury Transformations for Deep Generative Flows

You Lu, Bert Huang•Fri Jan 31 2020

Woodbury transformations are introduced, which achieve efficient invertibility via the Woodbury matrix identity and efficient determinant calculation via Sylvester's determinant identity and allow learning of higher-likelihood models than other flow architectures while still enjoying their efficiency advantages.

18 0

Paper Graph

Adding a benchmark result helps the community track progress.