Thesis

• Robust Accelerated Gradient Methods for Machine Learning

Alireza Fallah

        Master of Science in Electrical Engineering and Computer Science, Massachusetts Institute of Technology, June 2019.

Preprints

• Optimal Adaptive Testing for Epidemic Control: Combining Molecular and Serology Tests

       Daron Acemoglu*, Alireza Fallah*, Andrea Giometto*, Daniel Huttenlocher*, Asuman Ozdaglar*, Sarath Pattathil*

       Preprint: arXiv:2101.00773, 2021.

• Provably Convergent Policy Gradient Methods for Mode-Agnostic Meta-Reinforcement Learning 

Alireza Fallah, K. Georgiev, Aryan Mokhtari, Asuman Ozdaglar

       Preprint: arXiv: 2002.05135, 2020.

• Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks

Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar

       Preprint: arXiv: arXiv:2102.03832, 2021.

• Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks

Alireza Fallah*, Mert Gürbüzbalaban*, Asuman Ozdaglar*, Umut Simsekli*, Lingjiong Zhu*

       Preprint: arXiv: 1910.08701, 2019.

Conference Papers

• Private Adaptive Gradient Methods for Convex Optimization

       Hilal Asi*, John Duchi*, Alireza Fallah*, Omid Javidbakht*, Kunal Talwar*.

       International Conference in Machine Learning (ICML), 2021.

• A Wasserstein Minimax Framework for Mixed Linear Regression 

       Theo Diamandis*, Yonina Eldar*, Alireza Fallah*, Farzan Farnia*, Asuman Ozdaglar*.

       International Conference in Machine Learning (ICML), 2021.

• Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach 

Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar

      Advances in Neural Information Processing Systems (NeurIPS), 2020.

• On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms

Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar

       International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.

• An Optimal Multistage Stochastic Gradient Method for Minimax Problems

Alireza Fallah*,  Asuman Ozdaglar*, Sarath Pattathil*

       IEEE Conference on Decision and Control (CDC), 2020.

• A Universally Optimal Multistage Accelerated Stochastic Gradient Method

Necdet Serhat Aybat*, Alireza Fallah*, Mert Gürbüzbalaban*, Asuman Ozdaglar*

Advances in Neural Information Processing Systems (NeurIPS), 2019.

Journal Publications

• Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions

Necdet Serhat Aybat*, Alireza Fallah*, Mert Gürbüzbalaban*, Asuman Ozdaglar*

      SIAM Journal on Optimization (SIOPT), Volume 30, Issue 1, pages 717-751, 2020.

• Multidimensional Lévy White Noise in Weighted Besov Spaces

Julien Fageot*, Alireza Fallah*, Michael Unser*

Stochastic Processes and their Applications, Volume 127, Issue 5, 2017.

• Sampling and Distortion Tradeoffs for Indirect Source Retrieval

Elahe Mohammadi, Alireza Fallah, Farokh Marvasti

IEEE Transactions on Information Theory, vol. 63, no. 11, pp. 6833-6848, 2017.

Also, this paper presented partially at 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

*: Names arranged in alphabetic order.