2025
Asymmetric Duos: Sidekicks Improve Uncertainty.
CoRR, May, 2025
2024
Pathologies of Predictive Diversity in Deep Ensembles.
Trans. Mach. Learn. Res., 2024
Theoretical Limitations of Ensembles in the Age of Overparameterization.
CoRR, 2024
How Useful is Intermittent, Asynchronous Expert Feedback for Bayesian Optimization?
CoRR, 2024
Online Continual Learning of Video Diffusion Models From a Single Video Stream.
CoRR, 2024
Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning.
CoRR, 2024
Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Approximation-Aware Bayesian Optimization.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Large-Scale Gaussian Processes via Alternating Projection.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024
2023
CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Sharp Calibrated Gaussian Processes.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
2022
Convolutional Networks with Dense Connectivity.
IEEE Trans. Pattern Anal. Mach. Intell., 2022
Variational Nearest Neighbor Gaussian Processes.
CoRR, 2022
Posterior and Computational Uncertainty in Gaussian Processes.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Deep Ensembles Work, But Are They Necessary?
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Variational nearest neighbor Gaussian process.
Proceedings of the International Conference on Machine Learning, 2022
Preconditioning for Scalable Gaussian Process Hyperparameter Optimization.
Proceedings of the International Conference on Machine Learning, 2022
2021
Reducing the Variance of Gaussian Process Hyperparameter Optimization with Preconditioning.
CoRR, 2021
Scalable Cross Validation Losses for Gaussian Process Models.
CoRR, 2021
Hierarchical Inducing Point Gaussian Process for Inter-domain Observations.
CoRR, 2021
The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Rectangular Flows for Manifold Learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Bias-Free Scalable Gaussian Processes via Randomized Truncations.
Proceedings of the 38th International Conference on Machine Learning, 2021
Hierarchical Inducing Point Gaussian Process for Inter-domian Observations.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021
2020
Deep Sigma Point Processes.
Proceedings of the Thirty-Sixth Conference on Uncertainty in Artificial Intelligence, 2020
Fast Matrix Square Roots with Applications to Gaussian Processes and Bayesian Optimization.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Identifying Mislabeled Data using the Area Under the Margin Ranking.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Parametric Gaussian Process Regressors.
Proceedings of the 37th International Conference on Machine Learning, 2020
Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving.
Proceedings of the 8th International Conference on Learning Representations, 2020
Uses and Abuses of the Cross-Entropy Loss: Case Studies in Modern Deep Learning.
Proceedings of the "I Can't Believe It's Not Better!" at NeurIPS Workshops, 2020
2019
Sparse Gaussian Process Regression Beyond Variational Inference.
CoRR, 2019
Exact Gaussian Processes on a Million Data Points.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
2018
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
Constant-Time Predictive Distributions for Gaussian Processes.
Proceedings of the 35th International Conference on Machine Learning, 2018
Product Kernel Interpolation for Scalable Gaussian Processes.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018
2017
Memory-Efficient Implementation of DenseNets.
CoRR, 2017
On Fairness and Calibration.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017
On Calibration of Modern Neural Networks.
Proceedings of the 34th International Conference on Machine Learning, 2017
Snapshot Ensembles: Train 1, Get M for Free.
Proceedings of the 5th International Conference on Learning Representations, 2017
Deep Feature Interpolation for Image Content Changes.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017