Publications

Zak Mhammedi, James Cohan (2026). Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration. arXiv preprint arXiv:2603.22273.

Pre-Print Blog Post

Zak Mhammedi, Alexander Rakhlin, Nneka Okolo (2026). End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic Transitions. arXiv preprint arXiv:2603.23461.

Ruichen Jiang, Zak Mhammedi, Mehryar Mohri, Aryan Mokhtari (2026). Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization. arXiv preprint arXiv:2602.08232.

Zak Mhammedi (2025). An Ellipsoid Algorithm for Online Convex Optimization. NeurIPS 2025.

Sikata Bela Sengupta, Zak Mhammedi, T. V. Marinov (2025). Oracle-Efficient Adversarial Reinforcement Learning via Max-Following. The Exploration in AI Today Workshop at ICML 2025.

Dylan J. Foster, Zak Mhammedi, Dhruv Rohatgi (2025). Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration. arXiv preprint arXiv:2503.07453.

Zak Mhammedi, Dylan J. Foster, Alexander Rakhlin (2024). The Power of Resets in Online Reinforcement Learning. NeurIPS 2024.

Daniel Pfrommer, Swati Padmanabhan, Kwangjun Ahn, Jack Umenberger, Tobia Marcucci, Zak Mhammedi, Ali Jadbabaie (2024). On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control. IEEE 63rd Conference on Decision and Control (CDC 2024).

Ashok Cutkosky, Zak Mhammedi (2024). Fully Unconstrained Online Learning. NeurIPS 2024.

Haolin Liu, Zak Mhammedi, Chen-Yu Wei, Julian Zimmert (2024). Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback. NeurIPS 2024.

Zak Mhammedi (2024). Online Convex Optimization with a Separation Oracle. arXiv preprint arXiv:2410.02476.

Daniel Pfrommer, Swati Padmanabhan, Kwangjun Ahn, Jack Umenberger, Tobia Marcucci, Zak Mhammedi, Ali Jadbabaie (2024). Improved Sample Complexity of Imitation Learning for Barrier Model Predictive Control. arXiv preprint arXiv:2410.00859.

Zak Mhammedi (2024). Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value Functions. arXiv preprint arXiv:2409.04840.

Philip Amortila, Dylan J. Foster, Nan Jiang, Akshay Krishnamurthy, Zak Mhammedi (2024). Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity. ICML 2024.

Zak Mhammedi, Adam Block, Dylan J. Foster, Alexander Rakhlin (2023). Efficient Model-Free Exploration in Low-Rank MDPs. Pre-Print 2023.

Zak Mhammedi, Gatmiry Khashayar (2023). Quasi-Newton Steps for Efficient Online Exp-Concave Optimization. arXiv preprint arXiv:2211.01357.

Zak Mhammedi, Dylan J. Foster, Alexander Rakhlin (2023). Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL. ICML 2023.

Peter D. Grunwald, Muriel F. Perez-Ortiz, Zak Mhammedi (2023). Exponential Stochastic Inequality. arXiv preprint arXiv:2304.14217.

Kwangjun Ahn, Zak Mhammedi, Horia Mania, Zhang-Wei Hong, Ali Jadbabaie (2022). Model Predictive Control via On-Policy Imitation Learning. arXiv preprint arXiv:2210.09206.

Zak Mhammedi (2022). Exploiting the Curvature of Feasible Sets for Faster Projection-Free Online Learning. arXiv.

Zak Mhammedi, Alexander Rakhlin (2022). Damped Online Newton Step for Portfolio Selection. arXiv preprint arXiv:2202.07574.

Zak Mhammedi (2021). Efficient Projection-Free Online Convex Optimization with Membership Oracle. arXiv:2111.05818 [math, cs].

Zak Mhammedi (2021). Risk-Monotonicity in Statistical Learning. arXiv:2011.14126 [cs, stat].

Zak Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford (2020). Learning the Linear Quadratic Regulator from Nonlinear Observations. arXiv:2010.03799 [cs, math, stat].

Pre-Print Poster

Zak Mhammedi, Wouter M. Koolen (2020). Lipschitz and Comparator-Norm Adaptivity in Online Learning. Conference on Learning Theory.

Zak Mhammedi, Benjamin Guedj, Robert C. Williamson (2020). PAC-Bayesian Bound for the Conditional Value at Risk. arXiv:2006.14763 [cs, stat].

Pre-Print Poster

Zak Mhammedi, Wouter M. Koolen, Tim Van Erven (2019). Lipschitz Adaptivity with Multiple Learning Rates in Online Learning. Conference on Learning Theory.

Zak Mhammedi, Peter Grünwald, Benjamin Guedj (2019). PAC-Bayes Un-Expected Bernstein Inequality. Advances in Neural Information Processing Systems 32.

Soumava Kumar Roy, Zak Mhammedi, Mehrtash Harandi (2018). Geometry Aware Constrained Optimization Techniques for Deep Learning. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Zak Mhammedi, Robert C Williamson (2018). Constant Regret, Generalized Mixability, and Mirror Descent. NeurIPS 2018.

Zak Mhammedi, Andrew Hellicar, Ashfaqur Rahman, James Bailey (2017). Efficient orthogonal parametrisation of Recurrent Neural Networks using householder reflections. Proceedings of the 34th International Conference on Machine Learning - Volume 70.

Xingjun Ma, Sudanthi Wijewickrema, Shuo Zhou, Yun Zhou, Zakaria Mhammedi, Stephen O'Leary, James Bailey (2017). Adversarial Generation of Real-time Feedback with Neural Networks for Simulation-based Training. Electronic proceedings of IJCAI 2017.