Invited Talk: BORE — Bayesian Optimization by Density-Ratio Estimation
ELLIS AutoML Seminars (virtual).
A Primer on Pólya-gamma Random Variables - Part III: Local Variational Methods
We swap Gibbs sampling for mean-field variational inference in the Pólya-Gamma augmented model and watch the classical Jaakkola-Jordan bound on the logistic sigmoid fall out, EM …
BORE: Bayesian Optimization by Density-Ratio Estimation
We reformulate the computation of the acquisition function in Bayesian optimization (BO) as a probabilistic classification problem, providing advantages in scalability, …
A Primer on Pólya-gamma Random Variables - Part II: Bayesian Logistic Regression
We use one weird trick — Pólya-Gamma augmentation — to make exact inference in Bayesian logistic regression tractable.
A Primer on Pólya-gamma Random Variables - Part I: Basic Relationships
We collect the identities that make the Pólya-Gamma augmentation tick: the logistic sigmoid in terms of the hyperbolic cosine, the hyperbolic cosine as a Pólya-Gamma Laplace …
Contributed Talk: BORE — Bayesian Optimization by Density-Ratio Estimation
NeurIPS 2020 4th Workshop on Meta-Learning (virtual).
Bayesian Optimization by Density Ratio Estimation
📄 One paper accepted to NeurIPS 2020
Our paper "Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings" was accepted to NeurIPS 2020 as a Spotlight Presentation …
Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
We propose a joint probabilistic model with stochastic variational inference to improve the performance and robustness of graph convolutional networks (GCNs) in scenarios without …
Pantelis Elinas
Variational Graph Convolutional Networks