paper-with-me

Papers

Neural Spline Flows

2019-06-10 · NeurIPS 2019 12 · Conor Durkan, Artur Bekasov, Iain Murray, George Papamakarios

A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the parameterization of an easily invertible elementwise transformation, whose choice determines the flexibility of these models. Building upon recent work, we propose a fully-differentiable module based on monotonic rational-quadratic splines, which enhances the flexibility of both coupling and autoregressive transforms while retaining analytic invertibility. We demonstrate that neural spline flows improve density estimation, variational inference, and generative modeling of images.

📄 PDF Abstract BibTeX arXiv:1906.04032

Code (8)

bayesiains/nsf 공식 구현 pytorch
davidreiman/spectre pytorch
francois-rozet/zuko pytorch
jfcrenshaw/pzflow jax
johannbrehmer/manifold-flow pytorch
johnpjust/nsf pytorch
mackelab/nflows-nofork pytorch
https://gitlab.com/i-flow/i-flow tf

Tasks

Density EstimationVariational Inference

Similar Papers 제목 키워드 기반

Neural Diffeomorphic Non-uniform B-spline Flows

2023-04-07 · Seongmin Hong, Se Young Chun

Normalizing flows have been successfully modeling a complex probability distribution as an invertible transformation of a simple base distribution. However, there are often applications that require more than invertibili…

Cubic-Spline Flows

2019-06-05 · Conor Durkan, Artur Bekasov, Iain Murray, George Papamakarios

A normalizing flow models a complex probability density as an invertible transformation of a simple density. The invertibility means that we can evaluate densities and generate samples from a flow. In practice, autoregre…

Density Estimation

Generative Modeling for Low Dimensional Speech Attributes with Neural Spline Flows

2022-03-03 · Kevin J. Shih, Rafael Valle, Rohan Badlani, João Felipe Santos 외

Despite recent advances in generative modeling for text-to-speech synthesis, these models do not yet have the same fine-grained adjustability of pitch-conditioned deterministic models such as FastPitch and FastSpeech2. P…

Speech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Likelihood-free inference of experimental Neutrino Oscillations using Neural Spline Flows

2020-02-21 · Sebastian Pina-Otey, Federico Sánchez, Vicens Gaitan, Thorsten Lux

In machine learning, likelihood-free inference refers to the task of performing an analysis driven by data instead of an analytical expression. We discuss the application of Neural Spline Flows, a neural density estimati…

BIG-bench Machine LearningDensity Estimation

Spline-based Transformers

2025-04-03 · Prashanth Chandran, Agon Serifi, Markus Gross, Moritz Bächer

We introduce Spline-based Transformers, a novel class of Transformer models that eliminate the need for positional encoding. Inspired by workflows using splines in computer animation, our Spline-based Transformers embed …