Nov 3, 2021
Asymptotically Best Causal Effect Identification with Multi-Armed Bandits
Date: November 3, 2021 |
4:00 pm –
6:00 pm
Speaker:
Silvia Chiappa, DeepMind London
Location: Zoom Link: https://istaustria.zoom.us/j/92619096752?pwd=UWlEYTZ6UGUrSEZWMDNMMDltaEEzUT09 , Meeting ID: 926 1909 6752, Passcode: 189793
In this talk, I will present a method for selecting the causal identification formula with lowest asymptotic variance among a set of available ones. The method assumes an online setting in which the investigator may alter the data collection mechanism in a data-dependent way with the aim of identifying the formula in as few samples as possible, and formalizes this setting using the best-arm-identification bandit framework where the standard goal of learning the arm with the lowest loss is replaced with the goal of learning the arm that will produce the best estimate.