Oscar Key

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 13

Top Topics

Variational Inference

Top Venues

J. Mach. Learn. Res.

Publications

Oscar Key, So Takao, Daniel Giles, Marc Peter Deisenroth
Scalable Data Assimilation with Message Passing. CoRR (2024)
Jean Kaddour, Oscar Key, Piotr Nawrot, Pasquale Minervini, Matt J. Kusner
No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models. NeurIPS (2023)
Ayush Bharti, Masha Naslidnyk, Oscar Key, Samuel Kaski, François-Xavier Briol
Optimally-weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference. ICML (2023)
Jean Kaddour, Oscar Key, Piotr Nawrot, Pasquale Minervini, Matt J. Kusner
No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models. CoRR (2023)
Mingtian Zhang, Oscar Key, Peter Hayes, David Barber, Brooks Paige, François-Xavier Briol
Towards Healing the Blindness of Score Matching. CoRR (2022)
Aidan N. Gomez, Oscar Key, Kuba Perlin, Stephen Gou, Nick Frosst, Jeff Dean, Yarin Gal
Interlocking Backpropagation: Improving depthwise model-parallelism. J. Mach. Learn. Res. 23 (2022)
Lisa Schut, Oscar Key, Rory McGrath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties. AISTATS (2021)
Joost van Amersfoort, Lewis Smith, Andrew Jesson, Oscar Key, Yarin Gal
Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression. CoRR (2021)
Lisa Schut, Oscar Key, Rory McGrath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties. CoRR (2021)
Tim G. J. Rudner, Oscar Key, Yarin Gal, Tom Rainforth
On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes. ICML (2021)
Oscar Key, Tamara Fernandez, Arthur Gretton, François-Xavier Briol
Composite Goodness-of-fit Tests with Kernels. CoRR (2021)
Aidan N. Gomez, Oscar Key, Stephen Gou, Nick Frosst, Jeff Dean, Yarin Gal
Interlocking Backpropagation: Improving depthwise model-parallelism. CoRR (2020)
Tim G. J. Rudner, Oscar Key, Yarin Gal, Tom Rainforth
On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes. CoRR (2020)