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.

Publications

• Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms

       with Ali Makhdoumi, Azarakhsh Malekian, and Asuman Ozdaglar

        – Accepted to ACM Conference on Economics and Computation (EC), 2022 (extended abstract).

        – Minor revision, Operations Research, 2022.

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

with Aryan Mokhtari and Asuman Ozdaglar

      Advances in Neural Information Processing Systems (NeurIPS), 2021.

• On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning

with Kristian Georgiev, Aryan Mokhtari, and Asuman Ozdaglar

      Advances in Neural Information Processing Systems (NeurIPS), 2021.

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

       with Daron Acemoglu, Andrea Giometto, Daniel Huttenlocher, Asuman Ozdaglar, and Sarath Pattathil

       Preprint, 2021.

• Entropic Compressibility of Lévy Processes   

      with Julien Fageot and Thibaut Horel.

      To appear in IEEE Transactions on Information Theory, 2022.

• Private Adaptive Gradient Methods for Convex Optimization

       with Hilal Asi, John Duchi, Omid Javidbakht, and Kunal Talwar.

       International Conference in Machine Learning (ICML), 2021.

• A Wasserstein Minimax Framework for Mixed Linear Regression

       with Theo Diamandis, Yonina Eldar, Farzan Farnia, and Asuman Ozdaglar.

       International Conference in Machine Learning (ICML), 2021.

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

with Aryan Mokhtari and Asuman Ozdaglar.

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

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

with Aryan Mokhtari and Asuman Ozdaglar.

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

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

with Mert Gürbüzbalaban, Asuman Ozdaglar, Umut Simsekli, and Lingjiong Zhu.

       Preprint, 2019.

• An Optimal Multistage Stochastic Gradient Method for Minimax Problems

with Asuman Ozdaglar and Sarath Pattathil.

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

• A Universally Optimal Multistage Accelerated Stochastic Gradient Method

with Necdet Serhat Aybat, Mert Gürbüzbalaban, and Asuman Ozdaglar.

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

• Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions

with Necdet Serhat Aybat, Mert Gürbüzbalaban, and Asuman Ozdaglar.

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

• Multidimensional Lévy White Noise in Weighted Besov Spaces

with Julien Fageot and Michael Unser.

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

• Sampling and Distortion Tradeoffs for Indirect Source Retrieval

with Elahe Mohammadi and Farokh Marvasti.

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

– 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).