Mohammad Shahverdikondori

PhD student.

prof_pic.jpg

ODY room 4-16

École Polytechnique Fédérale de Lausanne

Lausanne, Switzerland

I am currently pursuing my PhD at the College of Management of Technology at EPFL, under the supervision of Prof. Negar Kiyavash. My research focuses on multi-armed bandit problems, particularly in settings with structured arms, with additional interests in causal inference. Prior to this, I completed my Bachelor’s degree in Computer Science at Sharif University of Technology (2018-2023).

You can see my full CV here(last update: June 2026).

news

Jun 2026 Our paper “Graph-dependent regret bounds in multi-armed bandits with interference” has been accepted to UAI 2026.
Jun 2026 I will attend RLSS 2026 in Milan from June 3 to June 12, 2026.
May 2026 Our paper “Learning Peer Influence Probabilities with Linear Contextual Bandits” has been accepted to SIGKDD 2026.
May 2026 Our new paper, “Active Context Selection Improves Simple Regret in Contextual Bandits”, is now available on arXiv.
Apr 2026 I had a wonderful two-week visit with Prof. Nicolò Cesa-Bianchi and his group at Università degli Studi di Milano in April.
Feb 2026 Our new work on the “Neighborhood-Aware Graph Labeling Problem” is now available on arXiv.
Jan 2026 Our paper “Graph Learning is Suboptimal in Causal Bandits” has been accepted to AISTATS 2026.
Oct 2025 We have also posted “Learning Peer Influence Probabilities with Linear Contextual Bandits” on arXiv.
Oct 2025 Our preprint “Graph Learning is Suboptimal in Causal Bandits” is now available on arXiv.
May 2025 Our latest preprint, “Best Group Identification in Multi-Objective Bandits”, is now on arXiv.
Mar 2025 We released two new preprints on arXiv: “Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context” and “Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference”.
Nov 2024 The preprint version of our QWO paper on speeding up causal discovery in linear Gaussian models is now available on arXiv.
Sep 2024 Our paper “QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs” has been accepted for presentation at NeurIPS 2024.
Oct 2023 I started my PhD at EPFL :smile:
Apr 2023 Our preprint on aligning human action videos is now available on arXiv.