Bayesian Optimization by Density Ratio Estimation
Louis Tiao
Research Scientist
My name is Louis Tiao, and I graduated from one of Australia’s
top engineering schools with really good grades.
Now, I’m using my knowledge to help up-and-coming tech companies
make it in this competitive world.
📄 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
Model-based Asynchronous Hyperparameter and Neural Architecture Search
We introduce a model-based method for asynchronous multi-fidelity hyperparameter and neural architecture search that combines the strengths of asynchronous Hyperband and Gaussian …
Aaron Klein
Variational Graph Convolutional Networks
A Handbook for Sparse Variational Gaussian Processes
We summarize the notation, identities, and derivations underlying the sparse variational Gaussian process (SVGP) framework.
Tech Talk: Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
Amazon Machine Learning Community Tech Talk, Berlin.
Density Ratio Estimation for KL Divergence Minimization between Implicit Distributions
We show how to approximate the KL divergence (in fact, any f-divergence) between implicit distributions using density ratio estimation by probabilistic classification.
Building Probability Distributions with the TensorFlow Probability Bijector API
We illustrate how to build complicated probability distributions in a modular fashion using the Bijector API from TensorFlow Probability.
Contributed Talk: Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models (TAGDM), Stockholm.