Kiarash Banihashem

I am a second year PhD student in University of Maryland where I am fortunate to be advised by MohammadTaghi Hajiaghayi. I am broadly interested in theoretical computer science and algorithms, with applications to machine learning. Previously, I obtained my BSc from Sharif university and did a remote internship at MPI-SWS under the supervision of Goran Radanovic and Adish Singla.

Email: [my first name] at umd dot edu

Google Scholar, DBLP

Publications

Authors ordered alphabetically unless stated otherwise.

Power of Posted-price Mechanisms for Prophet Inequalities
Kiarash Banihashem, Mohammad Taghi Hajiaghayi, Dariusz Kowalski, Piotr Krysta, Jan Olkowski
SODA 2024

Dynamic Algorithms for Matroid Submodular Maximization
Kiarash Banihashem, Leyla Biabani, Samira Goudarzi, MohammadTaghi Hajiaghayi, Peyman Jabbarzade, Morteza Monemizadeh
SODA 2024

An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits
Kiarash Banihashem, MohammadTaghi Hajiaghayi, Suho Shin, Max Springer
NeurIPS 2023

Dynamic Non-monotone Submodular Maximization
Kiarash Banihashem, Leyla Biabani, Samira Goudarzi, MohammadTaghi Hajiaghayi, Peyman Jabbarzade, Morteza Monemizadeh
NeurIPS 2023

Bandit Social Learning under Myopic Behavior
Kiarash Banihashem, MohammadTaghi Hajiaghayi, Suho Shin, Aleksandrs Slivkins
NeurIPS 2023

Dynamic Constrained Submodular Optimization with Polylogarithmic Update Time
Kiarash Banihashem, Leyla Biabani, Samira Goudarzi, MohammadTaghi Hajiaghayi, Peyman Jabbarzade, Morteza Monemizadeh
ICML 2023

Run-Off Election: Improved Provable Defense against Data Poisoning Attacks
Keivan Rezaei*, Kiarash Banihashem*, Atoosa Chegini, Soheil Feizi (contribution order)
*equal contribution.
ICML 2023

Defense Against Reward Poisoning Attacks in Reinforcement Learning
Kiarash Banihashem, Adish Singla, Goran Radanovic (contribution order)
TMLR 2023

Optimal Sparse Recovery with Decision Stumps
Kiarash Banihashem, MohammadTaghi Hajiaghayi, Max Springer
AAAI 2023

Explicit Tradeoffs between Adversarial and Natural Distributional Robustness
Mazda Moayeri, Kiarash Banihashem, Soheil Feizi (contribution order)
NeurIPS 2022

Admissible Policy Teaching through Reward Design
Kiarash Banihashem, Adish Singla, Jiarui Gan, Goran Radanovic (contribution order)
AAAI 2022