Andrew Gordon Wilson

Compute-Optimal LLMs Provably Generalize Better with Scale ICLR 2025 Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences ICLR 2025 Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization ICML 2025 Fine-Tuning with Uncertainty-Aware Priors Makes Vision and Language Foundation Models More Reliable AISTATS 2025 Customizing the Inductive Biases of Softmax Attention using Structured Matrices ICML 2025 Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra ICML 2025 Position: Deep Learning is Not So Mysterious or Different ICML 2025 Position: Supervised Classifiers Answer the Wrong Questions for OOD Detection ICML 2025 Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks ICML 2025 Fortuna: A Library for Uncertainty Quantification in Deep Learning JMLR 2024 Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors AISTATS 2024 Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models NIPS 2024 Large Language Models Must Be Taught to Know What They Don’t Know NIPS 2024 Fine-Tuned Language Models Generate Stable Inorganic Materials as Text ICLR 2024 Compute Better Spent: Replacing Dense Layers with Structured Matrices ICML 2024 Transferring Knowledge From Large Foundation Models to Small Downstream Models ICML 2024 A Study of Bayesian Neural Network Surrogates for Bayesian Optimization ICLR 2024 Controllable Prompt Tuning For Balancing Group Distributional Robustness ICML 2024 Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI ICML 2024 Non-Vacuous Generalization Bounds for Large Language Models ICML 2024 Modeling Caption Diversity in Contrastive Vision-Language Pretraining ICML 2024 Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning ICML 2024 Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency ICML 2024 Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices NIPS 2024 User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems ICML 2023 Bayesian Optimization with Conformal Prediction Sets AISTATS 2023 A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks ICLR 2023 How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization ICLR 2023 Transfer Learning with Deep Tabular Models ICLR 2023 Learning Multimodal Data Augmentation in Feature Space ICLR 2023 The Lie Derivative for Measuring Learned Equivariance ICLR 2023 Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations ICLR 2023 Simple and Fast Group Robustness by Automatic Feature Reweighting ICML 2023 Function-Space Regularization in Neural Networks: A Probabilistic Perspective ICML 2023 Bayesian Model Selection, the Marginal Likelihood, and Generalization ICML 2022 Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders ICML 2022 Low-Precision Stochastic Gradient Langevin Dynamics ICML 2022 Low-precision arithmetic for fast Gaussian processes UAI 2022 Deconstructing the Inductive Biases of Hamiltonian Neural Networks ICLR 2022 Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes ICML 2022 Fast Adaptation with Linearized Neural Networks AISTATS 2021 Kernel Interpolation for Scalable Online Gaussian Processes AISTATS 2021 A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups ICML 2021 On the Model-Based Stochastic Value Gradient for Continuous Reinforcement Learning L4DC 2021 Semi-Supervised Learning with Normalizing Flows ICML 2020 Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data ICML 2020 Randomly Projected Additive Gaussian Processes for Regression ICML 2020 Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning ICLR 2020 There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average ICLR 2019 SWALP : Stochastic Weight Averaging in Low Precision Training ICML 2019 Exact Gaussian Processes on a Million Data Points NIPS 2019 Subspace Inference for Bayesian Deep Learning UAI 2019 Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning UAI 2019 Simple Black-box Adversarial Attacks ICML 2019 Function-Space Distributions over Kernels NIPS 2019 Change Surfaces for Expressive Multidimensional Changepoints and Counterfactual Prediction JMLR 2019 A Simple Baseline for Bayesian Uncertainty in Deep Learning NIPS 2019 Hierarchical Density Order Embeddings ICLR 2018 Constant-Time Predictive Distributions for Gaussian Processes ICML 2018 Learning Scalable Deep Kernels with Recurrent Structure JMLR 2017 Deep Kernel Learning AISTATS 2016