Austin Tripp
Austin is a PhD student in the Cambridge Machine Learning group, researching machine learning with a focus on scientific applications (especially chemistry and materials). He is supervised by José Miguel Hernández-Lobato and advised by Adrian Weller.
Before coming to Cambridge, he received a BASc in nanotechnology engineering from the University of Waterloo in Canada. He is funded by a C.T. Taylor scholarship from the Cambridge Trust.
For more information, visit his personal website.
Publications
Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction
Wenlin Chen, Austin Tripp, José Miguel Hernández-Lobato, 2022. (arXiv).
Abstract▼ URL
We propose Adaptive Deep Kernel Fitting with Implicit Function Theorem (ADKF-IFT), a novel framework for learning deep kernel Gaussian processes (GPs) by interpolating between meta-learning and conventional deep kernel learning. Our approach employs a bilevel optimization objective where we meta-learn generally useful feature representations across tasks, in the sense that task-specific GP models estimated on top of such features achieve the lowest possible predictive loss on average. We solve the resulting nested optimization problem using the implicit function theorem (IFT). We show that our ADKF-IFT framework contains previously proposed Deep Kernel Learning (DKL) and Deep Kernel Transfer (DKT) as special cases. Although ADKF-IFT is a completely general method, we argue that it is especially well-suited for drug discovery problems and demonstrate that it significantly outperforms previous state-of-the-art methods on a variety of real-world few-shot molecular property prediction tasks and out-of-domain molecular property prediction and optimization tasks.
An Evaluation Framework for the Objective Functions of De Novo Drug Design Benchmarks
Austin Tripp, Wenlin Chen, José Miguel Hernández-Lobato, 2022. (In ICLR 2022 Workshop on Machine Learning for Drug Discovery).
Abstract▼ URL
De novo drug design has recently received increasing attention from the machine learning community. It is important that the field is aware of the actual goals and challenges of drug design and the roles that de novo molecule design algorithms could play in accelerating the process, so that algorithms can be evaluated in a way that reflects how they would be applied in real drug design scenarios. In this paper, we propose a framework for critically assessing the merits of benchmarks, and argue that most of the existing de novo drug design benchmark functions are either highly unrealistic or depend upon a surrogate model whose performance is not well characterized. In order for the field to achieve its long-term goals, we recommend that poor benchmarks (especially logP and QED) be deprecated in favour of better benchmarks. We hope that our proposed framework can play a part in developing new de novo drug design benchmarks that are more realistic and ideally incorporate the intrinsic goals of drug design.