Louis Tiao

Louis Tiao

Research Scientist

Meta - New York, US

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.

Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings featured image

Graph Representation Learning

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

• Jun 1, 2020 • 1 min read

Model-based Asynchronous Hyperparameter and Neural Architecture Search featured image

Hyperparameter Optimization

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

• Mar 1, 2020 • 1 min read

Graph Representation Learning

Variational Graph Convolutional Networks

Louis Tiao

• Dec 1, 2019 • 1 min read

A Handbook for Sparse Variational Gaussian Processes featured image

Gaussian Processes

A Handbook for Sparse Variational Gaussian Processes

We summarize the notation, identities, and derivations underlying the sparse variational Gaussian process (SVGP) framework.

Louis Tiao

• Sep 13, 2019 • 22 min read

Generative Adversarial Networks

Tech Talk: Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference

Amazon Machine Learning Community Tech Talk, Berlin.

Louis Tiao

• Jun 15, 2019 1:00 PM — 2:00 PM • 1 min read

Density Ratio Estimation for KL Divergence Minimization between Implicit Distributions featured image

Information Theory

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.

Louis Tiao

• Aug 27, 2018 • 20 min read

Probability Theory

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.

Louis Tiao

• Jul 30, 2018 • 8 min read

Contributed Talk: Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference featured image

Generative Adversarial Networks

Contributed Talk: Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference

ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models (TAGDM), Stockholm.

Louis Tiao

• Jul 14, 2018 3:20 PM — 3:30 PM • 1 min read

Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference featured image

Generative Adversarial Networks

Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference

We derive cycle-consistent adversarial learning (CycleGAN) as a special case of variational inference in a latent-variable model with implicit priors, establishing a Bayesian …

Louis Tiao

• Jul 1, 2018 • 1 min read

A Tutorial on Variational Autoencoders with a Concise Keras Implementation featured image

Variational Inference

A Tutorial on Variational Autoencoders with a Concise Keras Implementation

We give an in-depth practical guide to variational autoencoders from a probabilistic perspective.

Louis Tiao

• Apr 20, 2016 • 24 min read