Follow
Leonard Berrada
Leonard Berrada
Research Scientist, DeepMind
Verified email at google.com
Title
Cited by
Cited by
Year
Smooth Loss Functions for Deep Top-k Classification
L Berrada, A Zisserman, MP Kumar
International Conference on Learning Representations, 2018
1122018
Unlocking high-accuracy differentially private image classification through scale
S De, L Berrada, J Hayes, SL Smith, B Balle
arXiv preprint arXiv:2204.13650, 2022
1032022
Training neural networks for and by interpolation
L Berrada, A Zisserman, MP Kumar
International Conference on Machine Learning, 2020
452020
Deep Frank-Wolfe For Neural Network Optimization
L Berrada, A Zisserman, MP Kumar
International Conference on Learning Representations, 2019
442019
Differentially private diffusion models generate useful synthetic images
S Ghalebikesabi, L Berrada, S Gowal, I Ktena, R Stanforth, J Hayes, S De, ...
arXiv preprint arXiv:2302.13861, 2023
192023
Trusting SVM for piecewise linear CNNs
L Berrada, A Zisserman, MP Kumar
International Conference on Learning Representations, 2017
192017
Make sure you're unsure: A framework for verifying probabilistic specifications
L Berrada, S Dathathri, K Dvijotham, R Stanforth, RR Bunel, J Uesato, ...
Advances in Neural Information Processing Systems 34, 11136-11147, 2021
17*2021
Comment on stochastic Polyak step-size: Performance of ALI-G
L Berrada, A Zisserman, MP Kumar
arXiv preprint arXiv:2105.10011, 2021
52021
A stochastic bundle method for interpolating networks
A Paren, L Berrada, RPK Poudel, MP Kumar
The Journal of Machine Learning Research 23 (1), 642-698, 2022
42022
Unlocking Accuracy and Fairness in Differentially Private Image Classification
L Berrada, S De, JH Shen, J Hayes, R Stanforth, D Stutz, P Kohli, ...
arXiv preprint arXiv:2308.10888, 2023
12023
ConvNets Match Vision Transformers at Scale
SL Smith, A Brock, L Berrada, S De
arXiv preprint arXiv:2310.16764, 2023
2023
Leveraging structure for optimization in deep learning
L Berrada
University of Oxford, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–12