6 citations · 6 across the 1 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023
An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits
Kiarash Banihashem, MohammadTaghi Hajiaghayi, Suho Shin +1
We present an oracle-efficient relaxation for the adversarial contextual bandits problem, where the contexts are sequentially drawn i.i.d from a known distribution and the cost seq…
cs.LG2023★ 6 cited
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…