paper-with-me

홈 › Papers

Normalizing Flows for Probabilistic Modeling and Inference

2019-12-05 · George Papamakarios, Eric Nalisnick, Danilo Jimenez Rezende, Shakir Mohamed, Balaji Lakshminarayanan

Normalizing flows provide a general mechanism for defining expressive probability distributions, only requiring the specification of a (usually simple) base distribution and a series of bijective transformations. There has been much recent work on normalizing flows, ranging from improving their expressive power to expanding their application. We believe the field has now matured and is in need of a unified perspective. In this review, we attempt to provide such a perspective by describing flows through the lens of probabilistic modeling and inference. We place special emphasis on the fundamental principles of flow design, and discuss foundational topics such as expressive power and computational trade-offs. We also broaden the conceptual framing of flows by relating them to more general probability transformations. Lastly, we summarize the use of flows for tasks such as generative modeling, approximate inference, and supervised learning.

📄 PDF Abstract BibTeX arXiv:1912.02762

Code (7)

StanleyN1/normalizing-flows pytorch
VishakhG/normalizing-flows pytorch
fdesanti/hyperion pytorch
friedmanroy/hi-generation pytorch
ispamm/realnvp-demo-pytorch pytorch
mackelab/nflows-nofork pytorch
https://gitlab.com/i-flow/i-flow tf

Similar Papers 제목 키워드 기반

Automatic variational inference with cascading flows

2021-02-09 · Luca Ambrogioni, Gianluigi Silvestri, Marcel van Gerven

The automation of probabilistic reasoning is one of the primary aims of machine learning. Recently, the confluence of variational inference and deep learning has led to powerful and flexible automatic inference methods t…

Variational Inference

Data-driven Modeling and Inference for Bayesian Gaussian Process ODEs via Double Normalizing Flows

2023-09-17 · Jian Xu, Shian Du, Junmei Yang, Xinghao Ding 외

Recently, Gaussian processes have been used to model the vector field of continuous dynamical systems, referred to as GPODEs, which are characterized by a probabilistic ODE equation. Bayesian inference for these models h…

Bayesian InferenceGaussian ProcessesTime SeriesTime Series Prediction

Delving into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling

2023-04-08 · CVPR 2023 1 · Yulin Liu, Haoran Liu, Yingda Yin, Yang Wang 외

Normalizing flows (NFs) provide a powerful tool to construct an expressive distribution by a sequence of trackable transformations of a base distribution and form a probabilistic model of underlying data. Rotation, as an…

Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling

2021-10-12 · ICLR 2022 4 · Gianluigi Silvestri, Emily Fertig, Dave Moore, Luca Ambrogioni

Normalizing flows have shown great success as general-purpose density estimators. However, many real world applications require the use of domain-specific knowledge, which normalizing flows cannot readily incorporate. We…

modelVariational Inference

Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling

2024-04-08 · CVPR 2024 1 · Olaf Dünkel, Tim Salzmann, Florian Pfaff

Normalizing flows have proven their efficacy for density estimation in Euclidean space, but their application to rotational representations, crucial in various domains such as robotics or human pose modeling, remains und…

Density Estimation