paper-with-me

홈 › Papers

Reparameterizing Distributions on Lie Groups

2019-03-07 · Luca Falorsi, Pim de Haan, Tim R. Davidson, Patrick Forré

Reparameterizable densities are an important way to learn probability distributions in a deep learning setting. For many distributions it is possible to create low-variance gradient estimators by utilizing a `reparameterization trick'. Due to the absence of a general reparameterization trick, much research has recently been devoted to extend the number of reparameterizable distributional families. Unfortunately, this research has primarily focused on distributions defined in Euclidean space, ruling out the usage of one of the most influential class of spaces with non-trivial topologies: Lie groups. In this work we define a general framework to create reparameterizable densities on arbitrary Lie groups, and provide a detailed practitioners guide to further the ease of usage. We demonstrate how to create complex and multimodal distributions on the well known oriented group of 3D rotations, $\operatorname{SO}(3)$, using normalizing flows. Our experiments on applying such distributions in a Bayesian setting for pose estimation on objects with discrete and continuous symmetries, showcase their necessity in achieving realistic uncertainty estimates.

📄 PDF Abstract BibTeX arXiv:1903.02958

Code (1)

pimdh/relie 공식 구현 pytorch

Tasks

Pose Estimation

Similar Papers 제목 키워드 기반

Equivariance-aware Architectural Optimization of Neural Networks

2022-10-11 · Kaitlin Maile, Dennis G. Wilson, Patrick Forré

Incorporating equivariance to symmetry groups as a constraint during neural network training can improve performance and generalization for tasks exhibiting those symmetries, but such symmetries are often not perfectly n…

Neural Architecture Search

Implicit Quantile Networks for Distributional Reinforcement Learning

2018-06-14 · ICML 2018 7 · Will Dabney, Georg Ostrovski, David Silver, Rémi Munos

In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN. We achieve this by using quantile regressio…

Atari GamesDistributional Reinforcement Learningquantile regressionregression+3

How to Characterize The Landscape of Overparameterized Convolutional Neural Networks

2020-12-01 · NeurIPS 2020 12 · Yihong Gu, Weizhong Zhang, Cong Fang, Jason D. Lee 외

For many initialization schemes, parameters of two randomly initialized deep neural networks (DNNs) can be quite different, but feature distributions of the hidden nodes are similar at each layer. With the help of a new …

Stochastic Backpropagation through Mixture Density Distributions

2016-07-19 · Alex Graves

The ability to backpropagate stochastic gradients through continuous latent distributions has been crucial to the emergence of variational autoencoders and stochastic gradient variational Bayes. The key ingredient is an …

Variational Inference

Variational Learning of Gaussian Process Latent Variable Models through Stochastic Gradient Annealed Importance Sampling

2024-08-13 · Jian Xu, Shian Du, Junmei Yang, Qianli Ma 외

Gaussian Process Latent Variable Models (GPLVMs) have become increasingly popular for unsupervised tasks such as dimensionality reduction and missing data recovery due to their flexibility and non-linear nature. An impor…

Dimensionality Reduction