| Efficient orthogonal parametrisation of recurrent neural networks using householder reflections Z Mhammedi, A Hellicar, A Rahman, J Bailey International Conference on Machine Learning, 2401-2409, 2017 | 170 | 2017 |
| Geometry aware constrained optimization techniques for deep learning SK Roy, Z Mhammedi, M Harandi Proceedings of the IEEE conference on computer vision and pattern …, 2018 | 74 | 2018 |
| Lipschitz and comparator-norm adaptivity in online learning Z Mhammedi, WM Koolen Conference on Learning Theory, 2858-2887, 2020 | 60 | 2020 |
| PAC-Bayes un-expected Bernstein inequality Z Mhammedi, P Grünwald, B Guedj Advances in Neural Information Processing Systems 32, 2019 | 52 | 2019 |
| Learning the linear quadratic regulator from nonlinear observations Z Mhammedi, DJ Foster, M Simchowitz, D Misra, W Sun, A Krishnamurthy, ... Advances in Neural Information Processing Systems 33, 14532-14543, 2020 | 48 | 2020 |
| Lipschitz adaptivity with multiple learning rates in online learning Z Mhammedi, WM Koolen, T Van Erven Conference on Learning Theory, 2490-2511, 2019 | 37 | 2019 |
| Efficient projection-free online convex optimization with membership oracle Z Mhammedi Conference on Learning Theory, 5314-5390, 2022 | 35 | 2022 |
| Pac-bayesian bound for the conditional value at risk Z Mhammedi, B Guedj, RC Williamson Advances in Neural Information Processing Systems 33, 17919-17930, 2020 | 25 | 2020 |
| Representation learning with multi-step inverse kinematics: An efficient and optimal approach to rich-observation rl Z Mhammedi, DJ Foster, A Rakhlin International Conference on Machine Learning, 24659-24700, 2023 | 24 | 2023 |
| Efficient model-free exploration in low-rank mdps Z Mhammedi, A Block, DJ Foster, A Rakhlin Advances in Neural Information Processing Systems 36, 66782-66817, 2023 | 20 | 2023 |
| Recurrent neural networks for one day ahead prediction of stream flow Z Mhammedi, A Hellicar, A Rahman, K Kasfi, P Smethurst Proceedings of the Workshop on Time Series Analytics and Applications, 25-31, 2016 | 19 | 2016 |
| Damped online Newton step for portfolio selection Z Mhammedi, A Rakhlin Conference on learning theory, 5561-5595, 2022 | 17 | 2022 |
| Adversarial generation of real-time feedback with neural networks for simulation-based training X Ma, S Wijewickrema, S Zhou, Y Zhou, Z Mhammedi, S O'Leary, J Bailey arXiv preprint arXiv:1703.01460, 2017 | 16 | 2017 |
| Risk monotonicity in statistical learning Z Mhammedi Advances in Neural Information Processing Systems 34, 10732-10744, 2021 | 12 | 2021 |
| Model predictive control via on-policy imitation learning K Ahn, Z Mhammedi, H Mania, ZW Hong, A Jadbabaie Learning for Dynamics and Control Conference, 1493-1505, 2023 | 10 | 2023 |
| Constant regret, generalized mixability, and mirror descent Z Mhammedi, RC Williamson Advances in Neural Information Processing Systems 31, 2018 | 8 | 2018 |
| Exploiting the curvature of feasible sets for faster projection-free online learning Z Mhammedi arXiv preprint arXiv:2205.11470, 2022 | 7 | 2022 |
| The power of resets in online reinforcement learning Z Mhammedi, DJ Foster, A Rakhlin arXiv preprint arXiv:2404.15417, 2024 | 6 | 2024 |
| Quasi-newton steps for efficient online exp-concave optimization Z Mhammedi, K Gatmiry The Thirty Sixth Annual Conference on Learning Theory, 4473-4503, 2023 | 5 | 2023 |
| Online Convex Optimization with a Separation Oracle Z Mhammedi arXiv preprint arXiv:2410.02476, 2024 | 2 | 2024 |
James BaileyProfessor, School of Computing and Information Systems, University of MelbourneE-mail megerősítve itt: unimelb.edu.au