Showing 2023Show 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.DS2023
Dynamic Non-monotone Submodular Maximization
Kiarash Banihashem, Leyla Biabani, Samira Goudarzi +3
Maximizing submodular functions has been increasingly used in many applications of machine learning, such as data summarization, recommendation systems, and feature selection. More…