Mahmoud (Mido) Assran
Mahmoud (Mido) Assran
Andere namenMido Assran, Mahmoud Assran
Research Scientist at Meta AI (FAIR)
Geverifieerd e-mailadres voor meta.com - Homepage
Geciteerd door
Geciteerd door
Stochastic gradient push for distributed deep learning
M Assran, N Loizou, N Ballas, M Rabbat
ICML - International Conference on Machine Learning 97, 344-353, 2019
Dinov2: Learning robust visual features without supervision
M Oquab, T Darcet, T Moutakanni, H Vo, M Szafraniec, V Khalidov, ...
arXiv preprint arXiv:2304.07193, 2023
Masked siamese networks for label-efficient learning
M Assran, M Caron, I Misra, P Bojanowski, F Bordes, P Vincent, A Joulin, ...
ECCV - European Conference on Computer Vision, 2022
Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples
M Assran, M Caron, I Misra, P Bojanowski, A Joulin, N Ballas, M Rabbat
ICCV - IEEE/CVF International Conference on Computer Vision, 8443-8452, 2021
Asynchronous gradient-push
M Assran, M Rabbat
IEEE Transactions on Automatic Control 66 (1), 168-183, 2021
Advances in asynchronous parallel and distributed optimization
M Assran, A Aytekin, H Feyzmahdavian, M Johansson, M Rabbat
Proceedings of the IEEE 108 (11), 2013-2031, 2020
On the convergence of Nesterov's accelerated gradient method in stochastic settings
M Assran, M Rabbat
ICML - International Conference on Machine Learning 119, 410-420, 2020
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
M Assran, Q Duval, I Misra, P Bojanowski, P Vincent, M Rabbat, Y LeCun, ...
CVPR - IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Gossip-based actor-learner architectures for deep reinforcement learning
M Assran, J Romoff, N Ballas, J Pineau, M Rabbat
NeurIPS - Advances in Neural Information Processing Systems 32, 13320-13330, 2019
Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations
M Assran, N Ballas, L Castrejon, M Rabbat
NeurIPS - Workshop on Self-Supervised Learning, 2020
The hidden uniform cluster prior in self-supervised learning
M Assran, R Balestriero, Q Duval, F Bordes, I Misra, P Bojanowski, ...
ICLR - International Conference on Learning Representations, 2022
An empirical comparison of multi-agent optimization algorithms
M Assran, M Rabbat
IEEE GlobalSIP - IEEE Global Conference on Signal and Information Processing, 2017
A closer look at codistillation for distributed training
S Sodhani, O Delalleau, M Assran, K Sinha, N Ballas, M Rabbat
arXiv preprint arXiv:2010.02838, 2020
Memory Augmented Optimizers for Deep Learning
PA McRae, P Parthasarathi, M Assran, S Chandar
ICLR - International Conference on Learning Representations, 2022
RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data
S Mo, JC Su, CY Ma, M Assran, I Misra, L Yu, S Bell
ICLR - International Conference on Learning Representations, 2023
Asynchronous subgradient push: Fast, robust, and scalable multi-agent optimization
M Assran
McGill University Libraries, 2018
Predicting masked tokens in stochastic locations improves masked image modeling
A Bar, F Bordes, A Shocher, M Assran, P Vincent, N Ballas, T Darrell, ...
arXiv preprint arXiv:2308.00566, 2023
Algorithmic Advances Towards Efficient Learning Machines
M Assran
McGill University (Canada), 2023
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–18