Akram Erraqabi
Akram Erraqabi
PhD Student, Mila / UdeM
Verified email at
Cited by
Cited by
Diet networks: thin parameters for fat genomics
A Romero, PL Carrier, A Erraqabi, T Sylvain, A Auvolat, E Dejoie, ...
arXiv preprint arXiv:1611.09340, 2016
Trading off rewards and errors in multi-armed bandits
A Erraqabi, A Lazaric, M Valko, E Brunskill, YE Liu
Artificial Intelligence and Statistics, 709-717, 2017
Image segmentation by iterative inference from conditional score estimation
A Romero, M Drozdzal, A Erraqabi, S Jégou, Y Bengio
arXiv preprint arXiv:1705.07450, 2017
Controlled sparsity via constrained optimization or: How i learned to stop tuning penalties and love constraints
J Gallego-Posada, J Ramirez, A Erraqabi, Y Bengio, S Lacoste-Julien
Advances in Neural Information Processing Systems 35, 1253-1266, 2022
A3t: Adversarially augmented adversarial training
A Erraqabi, A Baratin, Y Bengio, S Lacoste-Julien
arXiv preprint arXiv:1801.04055, 2018
Exploration-driven representation learning in reinforcement learning
A Erraqabi, M Zhao, MC Machado, Y Bengio, S Sukhbaatar, L Denoyer, ...
ICML 2021 Workshop on Unsupervised Reinforcement Learning, 2021
Pliable rejection sampling
A Erraqabi, M Valko, A Carpentier, O Maillard
International Conference on Machine Learning, 2121-2129, 2016
Temporal abstractions-augmented temporally contrastive learning: An alternative to the Laplacian in RL
A Erraqabi, MC Machado, M Zhao, S Sukhbaatar, A Lazaric, D Ludovic, ...
Uncertainty in Artificial Intelligence, 641-651, 2022
On random weights for texture generation in one layer CNNS
M Mongia, K Kumar, A Erraqabi, Y Bengio
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
On random weights for texture generation in one layer neural networks
M Mongia, K Kumar, A Erraqabi, Y Bengio
arXiv preprint arXiv:1612.06070, 2016
Flexible Learning of Sparse Neural Networks via Constrained Regularization
J Gallego-Posada, J Ramirez, A Erraqabi
NeurIPS 2021 Workshop LatinX in AI, 2021
Combining adaptive algorithms and hypergradient method: a performance and robustness study
A Erraqabi, N Le Roux
Rewards and errors in multi-arm bandits for interactive education
A Erraqabi, A Lazaric, M Valko, E Brunskill, YE Liu
Challenges in Machine Learning: Gaming and Education workshop at Neural …, 2016
The system can't perform the operation now. Try again later.
Articles 1–13