Bayesian optimization (BO) is among the most effective and widely-used blackbox optimization methods. BO proposes solutions according to an explore-exploit trade-off criterion encoded in an acquisition function, many of which are derived from the …
AutoGluon is a library that implements numerous state-of-the-art methods for asynchronously distributed hyperparameter optimization (HPO) and neural architecture search (NAS). I was a core developer of the [Gaussian process-based multi-fidelity searcher](https://autogluon.mxnet.io/api/autogluon.searcher.html#gpmultifidelitysearcher) module.
We propose a framework that lifts the capabilities of graph convolutional networks (GCNs) to scenarios where no input graph is given and increases their robustness to adversarial attacks. We formulate a joint probabilistic model that considers a …
We introduce a model-based asynchronous multi-fidelity method for hyperparameter and neural architecture search that combines the strengths of asynchronous Hyperband and Gaussian process-based Bayesian optimization. At the heart of our method is a …
We propose a framework that lifts the capabilities of graph convolutional networks (GCNs) to scenarios where no input graph is given and increases their robustness to adversarial attacks. We formulate a joint probabilistic model that considers a …
This post demonstrates how to approximate the KL divergence (in fact, any f-divergence) between implicit distributions, using density ratio estimation by probabilistic classification.