173 citations · 304 across the 18 of their papers we have counts for
18 papers
Materials Expert-Artificial Intelligence for Materials Discovery
Yanjun Liu, Milena Jovanovic, Krishnanand Mallayya +5
The advent of material databases provides an unprecedented opportunity to uncover predictive descriptors for emergent material properties from vast data space. However, common reli…
Bayesian Optimization with Conformal Prediction Sets
Samuel Stanton, Wesley Maddox, Andrew Gordon Wilson
Bayesian optimization is a coherent, ubiquitous approach to decision-making under uncertainty, with applications including multi-arm bandits, active learning, and black-box optimiz…
Low-Precision Arithmetic for Fast Gaussian Processes
Wesley J. Maddox, Andres Potapczynski, Andrew Gordon Wilson
Low-precision arithmetic has had a transformative effect on the training of neural networks, reducing computation, memory and energy requirements. However, despite its promise, low…
Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes
Gregory Benton, Wesley J. Maddox, Andrew Gordon Wilson
A broad class of stochastic volatility models are defined by systems of stochastic differential equations. While these models have seen widespread success in domains such as financ…
On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
Sanyam Kapoor, Wesley J. Maddox, Pavel Izmailov +1
Aleatoric uncertainty captures the inherent randomness of the data, such as measurement noise. In Bayesian regression, we often use a Gaussian observation model, where we control t…
Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders
Samuel Stanton, Wesley Maddox, Nate Gruver +4
Bayesian optimization (BayesOpt) is a gold standard for query-efficient continuous optimization. However, its adoption for drug design has been hindered by the discrete, high-dimen…
When are Iterative Gaussian Processes Reliably Accurate?
Wesley J. Maddox, Sanyam Kapoor, Andrew Gordon Wilson
While recent work on conjugate gradient methods and Lanczos decompositions have achieved scalable Gaussian process inference with highly accurate point predictions, in several impl…
Optimizing High-Dimensional Physics Simulations via Composite Bayesian Optimization
Wesley Maddox, Qing Feng, Max Balandat
Physical simulation-based optimization is a common task in science and engineering. Many such simulations produce image- or tensor-based outputs where the desired objective is a fu…
Conditioning Sparse Variational Gaussian Processes for Online Decision-making
Wesley J. Maddox, Samuel Stanton, Andrew Gordon Wilson
With a principled representation of uncertainty and closed form posterior updates, Gaussian processes (GPs) are a natural choice for online decision making. However, Gaussian proce…
Bayesian Optimization with High-Dimensional Outputs
Wesley J. Maddox, Maximilian Balandat, Andrew Gordon Wilson +1
Bayesian Optimization is a sample-efficient black-box optimization procedure that is typically applied to problems with a small number of independent objectives. However, in practi…
Fast Adaptation with Linearized Neural Networks
Wesley J. Maddox, Shuai Tang, Pablo Garcia Moreno +2
The inductive biases of trained neural networks are difficult to understand and, consequently, to adapt to new settings. We study the inductive biases of linearizations of neural n…
Kernel Interpolation for Scalable Online Gaussian Processes
Samuel Stanton, Wesley J. Maddox, Ian Delbridge +1
Gaussian processes (GPs) provide a gold standard for performance in online settings, such as sample-efficient control and black box optimization, where we need to update a posterio…
Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
Gregory W. Benton, Wesley J. Maddox, Sanae Lotfi +1
With a better understanding of the loss surfaces for multilayer networks, we can build more robust and accurate training procedures. Recently it was discovered that independently t…
Similarity of Neural Networks with Gradients
Shuai Tang, Wesley J. Maddox, Charlie Dickens +2
A suitable similarity index for comparing learnt neural networks plays an important role in understanding the behaviour of the highly-nonlinear functions, and can provide insights…
Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited
Wesley J. Maddox, Gregory Benton, Andrew Gordon Wilson
Neural networks appear to have mysterious generalization properties when using parameter counting as a proxy for complexity. Indeed, neural networks often have many more parameters…
Function-Space Distributions over Kernels
Gregory W. Benton, Wesley J. Maddox, Jayson P. Salkey +2
Gaussian processes are flexible function approximators, with inductive biases controlled by a covariance kernel. Learning the kernel is the key to representation learning and stron…
Subspace Inference for Bayesian Deep Learning
Pavel Izmailov, Wesley J. Maddox, Polina Kirichenko +3
Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Ba…
A Simple Baseline for Bayesian Uncertainty in Deep Learning
Wesley Maddox, Timur Garipov, Pavel Izmailov +2
We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning. Stochastic Weight Averaging (SWA),…