Photo of me

About

ahmed . khaled @ princeton . edu

Welcome to my tiny corner of the internet! I’m Ahmed, I work on optimization and machine learning. I’m a third-year Ph.D. student in the ECE department at Princeton University, advised by Prof. Chi Jin. I am interested in optimization in machine learning, and in federated learning.

In the past, I have been fortunate to intern at Meta AI, working with Aaron Defazio in the summer of 2023. 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. Prior to that, I did some research on accelerating the training of neural networks by with Prof. Amir Atiya.

Publications and Preprints

Directional Smoothness and Gradient Methods: Convergence and Adaptivity
Preprint (February 2024), with Aaron Mishkin, Yuanhao Wang, Aaron Defazio, and Robert M. Gower. (bibtex).
Tuning-Free Stochastic Optimization
Preprint (February 2024), with Chi Jin. (bibtex).
DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
Advances in Neural Information Processing Systems 35 (NeurIPS 2023), with Chi Jin and Konstantin Mishchenko. (bibtex).
Faster federated optimization under second-order similarity
The 11th International Conference on Learning Representations (ICLR 2023), with Chi Jin. (bibtex).
Better Theory for SGD in the Nonconvex World
Transactions on Machine Learning Research (TMLR) 2023, with Peter Richtárik. (bibtex). Original preprint arXiv:2002.03329 on arXiv since 2020.
Federated Optimization Algorithms with Random Reshuffling and Gradient Compression
Preprint (2022), with Abdurakhmon Sadiev, Grigory Malinovsky, Eduard Gorbunov, Igor Sokolov, Konstantin Burlachenko, and Peter Richtárik. (bibtex).
Proximal and Federated Random Reshuffling
The 39th International Conference on Machine Learning (ICML 2022), with Konstantin Mishchenko and Peter Richtárik. (bibtex).
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).
Random Reshuffling: Simple Analysis with Vast Improvements
Advances in Neural Information Processing Systems 33 (NeurIPS 2020), with Konstantin Mishchenko and Peter Richtárik. (bibtex).
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. (bibtex). Extends the workshop papers (a, b).
Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization
Journal version to appear in JOTA 2023, original preprint 2020, with Othmane Sebbouh, Nicolas Loizou, Robert M. Gower, and Peter Richtárik. (bibtex).
Distributed Fixed Point Methods with Compressed Iterates
Preprint (2019), with Sélim Chraibi, Dmitry Kovalev, Peter Richtárik, Adil Salim, and Martin Takáč. (bibtex).
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

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

Talks

On the Convergence of Local SGD on Identical and Heterogeneous Data
Federated Learning One World Seminar (2020). Video and Slides.