Mohsen Amiri
About me
Research Interests
- Reinforcement Learning
- Federated Learning
- Optimization
- Machine Learning
- Deep Learning
- Signal Processing
Education
Ph.D. in Computer and Systems Sciences (Sep. 2023 - Ongoing)
- Department of Computer and Systems Sciences (DSV), Stockholm University, Stockholm, Sweden
M. Sc. in Electrical Engineering – Digital Electronic Systems (Sep. 2019 - Sep. 2022)
- Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran
- Dissertation title: "Automatic epileptic seizure detection in EEG signals using sparse common spatial pattern and adaptive short-time Fourier transform-based synchrosqueezing transform", Grade: 20 (A+)
B. Sc. in Electrical Engineering – Electronics (July 2015 - Sep. 2019)
- Department of Electrical Engineering, Bu-Ali Sina University, Hamedan, Iran
- Project title: "Shearlet-based image despeckling algorithm using ant colony segmentation", Grade: 19.5 (A)
Honors and Awards
2019: Ranked 1st in Cumulative GPA among all electrical engineering B.Sc. students at Bu-Ali Sina University (GPA 17.35 out of 20)
2019: Selected as an educational talented student by Bu-Ali Sina University
Publications
A selection from Stockholm University publication database
-
On the Convergence of TD-Learning on Markov Reward Processes with Hidden States
2024. Mohsen Amiri, Sindri Magnússon.
ConferenceRead more about On the Convergence of TD-Learning on Markov Reward Processes with Hidden StatesWe investigate the convergence properties of Temporal Difference (TD) Learning on Markov Reward Processes (MRPs) with new structures for incorporating hidden state information. In particular, each state is characterized by both observable and hidden components, with the assumption that the observable and hidden parts are statistically independent. This setup differs from Hidden Markov Models and Partially Observable Markov Decision Models, in that here it is not possible to infer the hidden information from the state observations. Nevertheless, the hidden state influences the MRP through the rewards, rendering the reward sequence non-Markovian. We prove that TD learning, when applied only on the observable part of the states, converges to a fixed point under mild assumptions on the step-size. Furthermore, we characterize this fixed point in terms of the statistical properties of both the Markov chains representing the observable and hidden parts of the states. Beyond the theoretical results, we illustrate the novel structure on two application setups in communications. Furthermore, we validate our results through experimental evidence, showcasing the convergence of the algorithm in practice.
Show all publications by Mohsen Amiri at Stockholm University