Please help transcribe this video using our simple transcription tool. You need to be logged in to do so.


Using the ad placement problem as an example, we describe an intricate link between causation and the interpretation of experimental data in learning systems. Following the lead gives (a) a non-regret perspective on exploration/exploitation decisions, (b) means to leverage the fine structure of the causal graph, (c) interesting differential techniques, (d) plenty of open questions.

Questions and Answers

You need to be logged in to be able to post here.