About

Photo of me

ahmed.khaled@princeton.edu

Hello! I’m Ahmed, I work on optimization and machine learning. I’m a research scientist at Google DeepMind. Prior to that, I got my Ph.D. from Princeton University, advised by Prof. Chi Jin. I am interested in optimization in machine learning, and in federated learning.

In the past, I have previously interned at Amazon AWS AI, Google DeepMind, and at Meta FAIR. Before that, I interned in the group of Prof. Peter Richtárik at KAUST in the summers of 2019/2020, where I worked on the distributed & stochastic optimization. In undergrad, I did some research on accelerating the training of neural networks by with Prof. Amir Atiya.

Publications and Preprints

  1. Towards Easier-to-Tune Training Algorithms: New Results from AlgoPerf
    arXiv preprint arXiv:2610.13036, 2026, with Priya Kasimbeg, Aahlad Chandrabhatta, Yifan Wang, Andy Liu, Niccolò Ajroldi, David Tweedle, Xingyu (Alice) Yang, Isaac Patole, Frank Schneider, and George E. Dahl.

    [bibtex]

  2. Muon Does Not Converge on Convex Lipschitz Functions
    To appear in NeurIPS 2026, with Tetiana Parshakova, Michael Crawshaw, Guillaume Garrigos, and Robert M. Gower.

    [bibtex]

  3. MuonBP: Faster Muon via Block-Periodic Orthogonalization
    ICLR 2026, with Kaan Ozkara, Tao Yu, Mingyi Hong, and Youngsuk Park.

    [bibtex]

  4. Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration
    NeurIPS 2025, with Satyen Kale, Arthur Douillard, Chi Jin, Rob Fergus, and Manzil Zaheer.

    [bibtex]

  5. Directional Smoothness and Gradient Methods: Convergence and Adaptivity
    NeurIPS 2024, with Aaron Mishkin, Yuanhao Wang, Aaron Defazio, and Robert M. Gower.

    [bibtex]

  6. The Road Less Scheduled
    NeurIPS 2024 Oral, with Aaron Defazio, Xingyu (Alice) Yang, Harsh Mehta, Konstantin Mishchenko, and Ashok Cutkosky.

    [bibtex]

  7. Don’t Compress Gradients in Random Reshuffling: Compress Gradient Differences
    NeurIPS 2024, with Abdurakhmon Sadiev, Grigory Malinovsky, Eduard Gorbunov, Igor Sokolov, Konstantin Burlachenko, and Peter Richtárik. (Original preprint titled Federated Optimization Algorithms with Random Reshuffling and Gradient Compression).

    [bibtex]

  8. Tuning-Free Stochastic Optimization
    ICML 2024 Spotlight, with Chi Jin.

    [bibtex]

  9. DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
    Advances in Neural Information Processing Systems 36 (NeurIPS 2023), with Chi Jin and Konstantin Mishchenko.

    [bibtex]

  10. Faster federated optimization under second-order similarity
    The 11th International Conference on Learning Representations (ICLR 2023), with Chi Jin.

    [bibtex]

  11. Better Theory for SGD in the Nonconvex World
    Transactions on Machine Learning Research (TMLR) 2023, with Peter Richtárik. Original preprint arXiv:2002.03329 on arXiv since 2020.

    [bibtex]

  12. Proximal and Federated Random Reshuffling
    The 39th International Conference on Machine Learning (ICML 2022), with Konstantin Mishchenko and Peter Richtárik.

    [bibtex]

  13. FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning
    The 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022), with Elnur Gasanov, Samuel Horváth, and Peter Richtárik.

    [bibtex]

  14. Random Reshuffling: Simple Analysis with Vast Improvements
    Advances in Neural Information Processing Systems 33 (NeurIPS 2020), with Konstantin Mishchenko and Peter Richtárik.

    [bibtex]

  15. Tighter Theory for Local SGD on Identical and Heterogeneous Data
    The 23rd International Conference on Artificial Intelligence and Statistics (AISTATS) 2020, with Konstantin Mishschenko and Peter Richtárik. Extends the workshop papers (a, b).

    [bibtex]

  16. Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization
    Journal version in JOTA 2023, original preprint 2020, with Othmane Sebbouh, Nicolas Loizou, Robert M. Gower, and Peter Richtárik.

    [bibtex]

  17. Distributed Fixed Point Methods with Compressed Iterates
    Preprint (2019), with Sélim Chraibi, Dmitry Kovalev, Peter Richtárik, Adil Salim, and Martin Takáč.

    [bibtex]

  18. Applying Fast Matrix Multiplication to Neural Networks
    The 35th ACM/SIGAPP Symposium On Applied Computing (ACM SAC) 2020, with Amir F. Atiya and Ahmed H. Abdel-Gawad.

    [bibtex]

Workshop papers

  1. A novel analysis of gradient descent under directional smoothness
    5th Annual Workshop on Optimization for Machine Learning (OPT2023), with Aaron Mishkin, Aaron Defazio, and Robert M. Gower.

    [bibtex]

  2. Better Communication Complexity for Local SGD
    Oral presentation at the NeurIPS 2019 Workshop on Federated Learning for Data Privacy and Confidentiality, with Konstantin Mishschenko and Peter Richtárik.

    [bibtex]

  3. First Analysis of Local GD on Heterogenous Data
    NeurIPS 2019 Workshop on Federated Learning for Data Privacy and Confidentiality, with Konstantin Mishschenko and Peter Richtárik.

    [bibtex]

  4. Gradient Descent with Compressed Iterates
    NeurIPS 2019 Workshop on Federated Learning for Data Privacy and Confidentiality, with Peter Richtárik.

    [bibtex]

Talks

  1. On the Convergence of Local SGD on Identical and Heterogeneous Data
    Federated Learning One World Seminar (2020). Video and Slides
Powered by Hugo with Console Theme.