paper-with-me

Papers

Multi-Scale Continuous Normalizing Flows

2021-06-02 · Anonymous

We introduce a multi-scale variant of Continuous Normalizing Flows, and explore the computation of likelihood values. We also introduce a Wavelet-version of the model. However, we find that this formulation is flawed in the computation of BPD, and explore ways to alleviate this problem.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

Categorical Normalizing Flows via Continuous Transformations

2020-06-17 · ICLR 2021 1 · Phillip Lippe, Efstratios Gavves

Despite their popularity, to date, the application of normalizing flows on categorical data stays limited. The current practice of using dequantization to map discrete data to a continuous space is inapplicable as catego…

DecoderInductive BiasVariational Inference

Temporal Normalizing Flows

2019-12-19 · Remy Kusters, Gert-Jan Both

Analyzing and interpreting time-dependent stochastic data requires accurate and robust density estimation. In this paper we extend the concept of normalizing flows to so-called temporal Normalizing Flows (tNFs) to estima…

Density Estimation

Learning normalizing flows from Entropy-Kantorovich potentials

2020-06-10 · Chris Finlay, Augusto Gerolin, Adam M. Oberman, Aram-Alexandre Pooladian

We approach the problem of learning continuous normalizing flows from a dual perspective motivated by entropy-regularized optimal transport, in which continuous normalizing flows are cast as gradients of scalar potential…

Riemannian Continuous Normalizing Flows

2020-06-18 · NeurIPS 2020 12 · Emile Mathieu, Maximilian Nickel

Normalizing flows have shown great promise for modelling flexible probability distributions in a computationally tractable way. However, whilst data is often naturally described on Riemannian manifolds such as spheres, t…

Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows

2020-01-02 · Gavin S. Hartnett, Masoud Mohseni

Spin-glasses are universal models that can capture complex behavior of many-body systems at the interface of statistical physics and computer science including discrete optimization, inference in graphical models, and au…

Self-Supervised Learning