Oscar Key
Cytowane przez
Cytowane przez
On feature collapse and deep kernel learning for single forward pass uncertainty
J van Amersfoort, L Smith, A Jesson, O Key, Y Gal
arXiv preprint arXiv:2102.11409, 2021
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
L Schut, O Key, R Mc Grath, L Costabello, B Sacaleanu, Y Gal
International Conference on Artificial Intelligence and Statistics, 1756-1764, 2021
Interlocking Backpropagation: Improving depthwise model-parallelism
AN Gomez, O Key, K Perlin, S Gou, N Frosst, J Dean, Y Gal
Journal of Machine Learning Research 23 (171), 1-28, 2022
No train no gain: Revisiting efficient training algorithms for transformer-based language models
J Kaddour, O Key, P Nawrot, P Minervini, MJ Kusner
Advances in Neural Information Processing Systems 36, 2024
Composite goodness-of-fit tests with kernels
O Key, A Gretton, FX Briol, T Fernandez
arXiv preprint arXiv:2111.10275, 2021
Towards Healing the Blindness of Score Matching
M Zhang, O Key, P Hayes, D Barber, B Paige, FX Briol
arXiv preprint arXiv:2209.07396, 2022
Optimally-weighted estimators of the maximum mean discrepancy for likelihood-free inference
A Bharti, M Naslidnyk, O Key, S Kaski, FX Briol
International Conference on Machine Learning, 2289-2312, 2023
Local LoRA: Memory-Efficient Fine-Tuning of Large Language Models
O Key, J Kaddour, P Minervini
Workshop on Advancing Neural Network Training: Computational Efficiency …, 2023
On signal-to-noise ratio issues in variational inference for deep Gaussian processes
TGJ Rudner, O Key, Y Gal, T Rainforth
International Conference on Machine Learning, 9148-9156, 2021
Scalable Data Assimilation with Message Passing
O Key, S Takao, D Giles, MP Deisenroth
arXiv preprint arXiv:2404.12968, 2024
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–10