CV
Education
- University of Washington, Seattle, USA
- Ph.D. in Computer Science, 2025 - present
- Advisors: Kevin Jamieson & Lillian Ratliff
- University of Alberta, Edmonton, Canada
- M.Sc. in Computing Science, 2021 - 2025
- Advisor: Csaba Szepesvári
- GPA: 3.90/4
- Amirkabir University of Technology, Tehran, Iran
- B.Sc. in Computer Engineering, 2016 - 2021
- GPA: 17.83/20
Work experience
- Jul 2020 - Jul 2021: Software Engineer @ Evience
- Developed tools and models for systematic trading in cryptocurrency markets.
- Jul 2018 - Jul 2020: Software Engineer @ Sokan
- Devolped data intense backend and networking services in C++ and Python.
- May 2022 - present: Graduate Research Assistant @ University of Alberta
- Working on “Exploration via linearly perturbed loss minimisation” and “Self-concordance on natural exponential family”.
- Jun 2020 - Jun 2021: Research Assistant @ Harbin Institute of Technology
- Undergraduate thesis on “Self-Supervised Representation Learning in Gaze Estimation”.
- Jan 2020 - Nov 2020: Research Assistant @ University of California, Berkeley (ICSI)
- Project: “Unsupervised Feature Learning for Construction Identification”.
Skills
- Programming Languages and Tools: C++/Java/Python, PyTorch, Jax, Git, Vim
Honours and Awards
- Nominated for the best thesis award at University of Alberta (2025)
- Ranked 459 in the Nationwide University Entrance Exam (approx. 163,000 applicants) (2015)
- Ranked 43 in Iran’s National Olympiad in Informatics (approx. 5,500 applicants) (2013)
Publications
Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning
Volodymyr Tkachuk, Alireza Bakhtiari, Matej Jusup, Ilija Bogunovic, and Csaba Szepesvári. (2023). "Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning". AISTATS.
Regret Minimization via Saddle Point Optimization
Johannes Kirschner, Alireza Bakhtiari, Kushagra Chandak, Volodymyr Tkachuk, and Csaba Szepesvári. (2023). "Regret Minimization via Saddle Point Optimization". NeurIPS.
Efficient Simple Regret Algorithms for Stochastic Contextual Bandits
Shuai Liu, Alireza Bakhtiari, Alex Ayoub, Botao Hao, Tor Lattimore, Csaba Szepesvári. (2025). "Efficient Simple Regret Algorithms for Stochastic Contextual Bandits". Preprint.
Thompson Sampling for Bandit Convex Optimization
Alireza Bakhtiari, Tor Lattimore, and Csaba Szepesvári. (2025). "Thompson Sampling for Bandit Convex Optimization". COLT.
Rectifying Regression in Reinforcement Learning
Alex Ayoub, David Szepesvári, Alireza Bakhtiari, Csaba Szepesvári, Dale Schuurmans. (2025). "Rectifying Regression in Reinforcement Learning". RLC.
Eluder dimension: localise it!
Alireza Bakhtiari, Alex Ayoub, David Janz, Samuel Robertson, and Csaba Szepesvári. (2025). "Eluder dimension: localise it!". NeurIPS.
Talks
Amirkabir Linux Festival
Talk at Amirkabir university of Technology, Tehran, Iran