Picture for Kiarash Banihashem

Kiarash Banihashem

A Dynamic Algorithm for Weighted Submodular Cover Problem

Add code
Jul 13, 2024
Viaarxiv icon

Dynamic Non-monotone Submodular Maximization

Add code
Nov 07, 2023
Viaarxiv icon

An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits

Add code
Oct 29, 2023
Viaarxiv icon

Dynamic Algorithms for Matroid Submodular Maximization

Add code
Jun 01, 2023
Viaarxiv icon

Optimal Sparse Recovery with Decision Stumps

Add code
Mar 08, 2023
Viaarxiv icon

Bandit Social Learning: Exploration under Myopic Behavior

Add code
Feb 15, 2023
Viaarxiv icon

Run-Off Election: Improved Provable Defense against Data Poisoning Attacks

Add code
Feb 05, 2023
Viaarxiv icon

Explicit Tradeoffs between Adversarial and Natural Distributional Robustness

Add code
Sep 15, 2022
Figure 1 for Explicit Tradeoffs between Adversarial and Natural Distributional Robustness
Figure 2 for Explicit Tradeoffs between Adversarial and Natural Distributional Robustness
Figure 3 for Explicit Tradeoffs between Adversarial and Natural Distributional Robustness
Figure 4 for Explicit Tradeoffs between Adversarial and Natural Distributional Robustness
Viaarxiv icon

Admissible Policy Teaching through Reward Design

Add code
Jan 06, 2022
Figure 1 for Admissible Policy Teaching through Reward Design
Figure 2 for Admissible Policy Teaching through Reward Design
Figure 3 for Admissible Policy Teaching through Reward Design
Viaarxiv icon

Defense Against Reward Poisoning Attacks in Reinforcement Learning

Add code
Feb 10, 2021
Figure 1 for Defense Against Reward Poisoning Attacks in Reinforcement Learning
Figure 2 for Defense Against Reward Poisoning Attacks in Reinforcement Learning
Viaarxiv icon