Alireza Bakhtiari — accepted AI-conference papers

2025

Eluder dimension: localise it!

Alireza Bakhtiari, Alex Ayoub, Samuel McLaughlin Robertson, David Janz, Csaba Szepesvari

NeurIPS 2025spotlight

We establish a lower bound on the eluder dimension in generalised linear model classes, showing that standard eluder dimension-based analysis cannot lead to first-order regret bounds. To address this, we introduce a localisation method for the eluder dimension; our analysis immediately recovers and…

Cited by 0 Source ↗Scholar ↗

2023

Regret Minimization via Saddle Point Optimization

Johannes Kirschner, Alireza Bakhtiari, Kushagra Chandak, Volodymyr Tkachuk, Csaba Szepesvari

NeurIPS 2023poster

A long line of works characterizes the sample complexity of regret minimization in sequential decision-making by min-max programs. In the corresponding saddle-point game, the min-player optimizes the sampling distribution against an adversarial max-player that chooses confusing models leading to la…

Cited by 2 Source ↗PDF ↗Scholar ↗