Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Concentration Bounds for Optimized Certainty Equivalent Risk Estimation
Ayon Ghosh, L. A. Prashanth, Krishna Jagannathan
We consider the problem of estimating the Optimized Certainty Equivalent (OCE) risk from independent and identically distributed (i.i.d.) samples. For the classic sample average ap…
cs.LG2016
Bandit algorithms to emulate human decision making using probabilistic distortions
Ravi Kumar Kolla, Prashanth L. A., Aditya Gopalan +3
Motivated by models of human decision making proposed to explain commonly observed deviations from conventional expected value preferences, we formulate two stochastic multi-armed…