Published in NeurIPS, 2025
This paper was published in NeurIPS 2025 (Spotlight).
Recommended citation: Alireza Bakhtiari, Alex Ayoub, David Janz, Samuel Robertson, and Csaba Szepesvári. (2025). "Eluder dimension: localise it!". NeurIPS.
Published in RLC, 2025
This paper was published in RLC 2025.
Recommended citation: Alex Ayoub, David Szepesvári, Alireza Bakhtiari, Csaba Szepesvári, Dale Schuurmans. (2025). "Rectifying Regression in Reinforcement Learning". RLC.
Published in COLT, 2025
This paper was published in COLT 2025.
Recommended citation: Alireza Bakhtiari, Tor Lattimore, and Csaba Szepesvári. (2025). "Thompson Sampling for Bandit Convex Optimization". COLT.
Published in Preprint, 2025
Preprint.
Recommended citation: Shuai Liu, Alireza Bakhtiari, Alex Ayoub, Botao Hao, Tor Lattimore, Csaba Szepesvári. (2025). "Efficient Simple Regret Algorithms for Stochastic Contextual Bandits". Preprint.
Published in NeurIPS, 2023
This paper was published in NeurIPS 2023.
Recommended citation: Johannes Kirschner, Alireza Bakhtiari, Kushagra Chandak, Volodymyr Tkachuk, and Csaba Szepesvári. (2023). "Regret Minimization via Saddle Point Optimization". NeurIPS.
Published in AISTATS, 2023
This paper was published in AISTATS 2023.
Recommended citation: 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.
Published in Empirical Economics, 2021
Using Dual-Stage Attention-Based Recurrent Neural Network in forcasting cryptocurrency volatility and comparing results with other methods as well as hyperparameters.