Accelerating neural network training: An analysis of the AlgoPerf competition.
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
Pre-trained Gaussian Processes for Bayesian Optimization.
J. Mach. Learn. Res., 2024
A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness.
J. Mach. Learn. Res., 2023
Kernel Regression with Infinite-Width Neural Networks on Millions of Examples.
CoRR, 2023
Adaptive Gradient Methods at the Edge of Stability.
,
,
,
,
,
,
,
,
,
,
CoRR, 2022
Pre-training helps Bayesian optimization too.
CoRR, 2022
A Loss Curvature Perspective on Training Instabilities of Deep Learning Models.
Proceedings of the Tenth International Conference on Learning Representations, 2022
Predicting the utility of search spaces for black-box optimization: a simple, budget-aware approach.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022
A Loss Curvature Perspective on Training Instability in Deep Learning.
CoRR, 2021
Automatic prior selection for meta Bayesian optimization with a case study on tuning deep neural network optimizers.
CoRR, 2021
A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes.
CoRR, 2021
Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021
Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks.
CoRR, 2020
Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift.
CoRR, 2020
On Empirical Comparisons of Optimizers for Deep Learning.
CoRR, 2019
Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
AutoGraph: Imperative-style Coding with Graph-based Performance.
Proceedings of the Second Conference on Machine Learning and Systems, SysML 2019, 2019
Stochastic Gradient Langevin dynamics that Exploit Neural Network Structure.
Proceedings of the 6th International Conference on Learning Representations, 2018