paper-with-me

Papers

Variational Auto-encoded Deep Gaussian Processes

2015-11-19 · Zhenwen Dai, Andreas Damianou, Javier González, Neil Lawrence

We develop a scalable deep non-parametric generative model by augmenting deep Gaussian processes with a recognition model. Inference is performed in a novel scalable variational framework where the variational posterior distributions are reparametrized through a multilayer perceptron. The key aspect of this reformulation is that it prevents the proliferation of variational parameters which otherwise grow linearly in proportion to the sample size. We derive a new formulation of the variational lower bound that allows us to distribute most of the computation in a way that enables to handle datasets of the size of mainstream deep learning tasks. We show the efficacy of the method on a variety of challenges including deep unsupervised learning and deep Bayesian optimization.

📄 PDF Abstract BibTeX arXiv:1511.06455

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian OptimizationGaussian Processes

Similar Papers 제목 키워드 기반

DeepCoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding

2017-04-07 · ICCV 2017 10 · Dieu Linh Tran, Robert Walecki, Ognjen Rudovic, Stefanos Eleftheriadis 외

Human face exhibits an inherent hierarchy in its representations (i.e., holistic facial expressions can be encoded via a set of facial action units (AUs) and their intensity). Variational (deep) auto-encoders (VAE) have …

Gaussian Processes

GP-ALPS: Automatic Latent Process Selection for Multi-Output Gaussian Process Models

2019-11-05 · pproximateinference AABI Symposium 2019 12 · Pavel Berkovich, Eric Perim, Wessel Bruinsma

A simple and widely adopted approach to extend Gaussian processes (GPs) to multiple outputs is to model each output as a linear combination of a collection of shared, unobserved latent GPs. An issue with this approach is…

Gaussian ProcessesVariational Inference

Variational Elliptical Processes

2023-11-21 · Maria Bånkestad, Jens Sjölund, Jalil Taghia, Thomas B. Schöon

We present elliptical processes, a family of non-parametric probabilistic models that subsume Gaussian processes and Student's t processes. This generalization includes a range of new heavy-tailed behaviors while retaini…

Gaussian ProcessesVariational Inference

Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders

2020-01-08 · ECCV 2020 8 · Sarthak Bhagat, Shagun Uppal, Zhuyun Yin, Nengli Lim

We introduce MGP-VAE (Multi-disentangled-features Gaussian Processes Variational AutoEncoder), a variational autoencoder which uses Gaussian processes (GP) to model the latent space for the unsupervised learning of disen…

Gaussian ProcessesVideo Prediction

Variational Auto-Regressive Gaussian Processes for Continual Learning

2020-06-09 · Sanyam Kapoor, Theofanis Karaletsos, Thang D. Bui

Through sequential construction of posteriors on observing data online, Bayes' theorem provides a natural framework for continual learning. We develop Variational Auto-Regressive Gaussian Processes (VAR-GPs), a principle…

Bayesian InferenceContinual LearningGaussian Processes