9 citations · 24 across the 9 of their papers we have counts for
9 papers
Bandit Social Learning with Exploration Episodes
Kiarash Banihashem, Natalie Collina, Aleksandrs Slivkins
We study a stylized social learning dynamics where self-interested agents collectively follow a simple multi-armed bandit protocol. Each agent controls an ``episode": a short seque…
Dynamic Algorithms for Matroid Submodular Maximization
Kiarash Banihashem, Leyla Biabani, Samira Goudarzi +3
Submodular maximization under matroid and cardinality constraints are classical problems with a wide range of applications in machine learning, auction theory, and combinatorial op…
Dynamic Constrained Submodular Optimization with Polylogarithmic Update Time
Kiarash Banihashem, Leyla Biabani, Samira Goudarzi +3
Maximizing a monotone submodular function under cardinality constraint is a core problem in machine learning and database with many basic applications, including video and data…
Optimal Sparse Recovery with Decision Stumps
Kiarash Banihashem, MohammadTaghi Hajiaghayi, Max Springer
Decision trees are widely used for their low computational cost, good predictive performance, and ability to assess the importance of features. Though often used in practice for fe…
Bandit Social Learning: Exploration under Myopic Behavior
Kiarash Banihashem, MohammadTaghi Hajiaghayi, Suho Shin +1
We study social learning dynamics motivated by reviews on online platforms. The agents collectively follow a simple multi-armed bandit protocol, but each agent acts myopically, wit…
Run-Off Election: Improved Provable Defense against Data Poisoning Attacks
Keivan Rezaei, Kiarash Banihashem, Atoosa Chegini +1
In data poisoning attacks, an adversary tries to change a model's prediction by adding, modifying, or removing samples in the training data. Recently, ensemble-based approaches for…
Explicit Tradeoffs between Adversarial and Natural Distributional Robustness
Mazda Moayeri, Kiarash Banihashem, Soheil Feizi
Several existing works study either adversarial or natural distributional robustness of deep neural networks separately. In practice, however, models need to enjoy both types of ro…
Admissible Policy Teaching through Reward Design
Kiarash Banihashem, Adish Singla, Jiarui Gan +1
We study reward design strategies for incentivizing a reinforcement learning agent to adopt a policy from a set of admissible policies. The goal of the reward designer is to modify…
Defense Against Reward Poisoning Attacks in Reinforcement Learning
Kiarash Banihashem, Adish Singla, Goran Radanovic
We study defense strategies against reward poisoning attacks in reinforcement learning. As a threat model, we consider attacks that minimally alter rewards to make the attacker's t…