2 papers
cs.LG2024
p-Mean Regret for Stochastic Bandits
Anand Krishna, Philips George John, Adarsh Barik +1
In this work, we extend the concept of the -mean welfare objective from social choice theory (Moulin 2004) to study -mean regret in stochastic multi-armed bandit problems. Th…
cs.LG2024
LEARN: An Invex Loss for Outlier Oblivious Robust Online Optimization
Adarsh Barik, Anand Krishna, Vincent Y. F. Tan
We study a robust online convex optimization framework, where an adversary can introduce outliers by corrupting loss functions in an arbitrary number of rounds k, unknown to the le…