Arman Adibi — accepted AI-conference papers

2024

Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling

Arman Adibi, Nicolò Dal Fabbro, Luca Schenato, Sanjeev Kulkarni, H. Vincent Poor, George J. Pappas +2

AISTATS 2024poster

Motivated by applications in large-scale and multi-agent reinforcement learning, we study the non-asymptotic performance of stochastic approximation (SA) schemes with delayed updates under Markovian sampling. While the effect of delays has been extensively studied for optimization, the manner in whi…

Cited by 14 Source ↗PDF ↗Scholar ↗

2022

Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds

Aritra Mitra, Arman Adibi, George J. Pappas, Hamed Hassani

NeurIPS 2022accept

We consider a linear stochastic bandit problem involving $M$ agents that can collaborate via a central server to minimize regret. A fraction $\alpha$ of these agents are adversarial and can act arbitrarily, leading to the following tension: while collaboration can potentially reduce regret, it can a…

Cited by 9 Source ↗PDF ↗Scholar ↗

2022

Minimax Optimization: The Case of Convex-Submodular

Arman Adibi, Aryan Mokhtari, Hamed Hassani

AISTATS 2022poster

Minimax optimization has been central in addressing various applications in machine learning, game theory, and control theory. Prior literature has thus far mainly focused on studying such problems in the continuous domain, e.g., convex-concave minimax optimization is now understood to a significant…

Cited by 9 Source ↗PDF ↗Scholar ↗

2020

Submodular Meta-Learning

Arman Adibi, Aryan Mokhtari, Hamed Hassani

NeurIPS 2020poster

In this paper, we introduce a discrete variant of the Meta-learning framework. Meta-learning aims at exploiting prior experience and data to improve performance on future tasks. By now, there exist numerous formulations for Meta-learning in the continuous domain. Notably, the Model-Agnostic Meta-Lea…

Cited by 9 Source ↗PDF ↗Scholar ↗