And finally this super cool work — intervention-based learning of mixtures of DAGs, which are more powerful in abstracting the complexities of causal systems. We the usual suspects in the results: necessary & sufficient conditions for mixture recovery and an algorithm.
In addition to Burak’s work, Zirui will also present how to drop knowing the graph topology altogether — a major challenge in causal bandits, which has been understood for only do interventions. Zirui’s work addresses the general soft interventions setting #causality #bandits
Burak & Emre will be presenting two papers on causal representation learning: (1) finite-sample guarantees (identifiability & algorithmic) and (2) unknown, multi-target intervention. Further evidence that our score-based method is highly versatile apt for diverse settings.
Saying no can be an option sometimes :)
This is very well deserved!
True for implementation. Analysis needs (non-trivial) probability analysis and in-depth understanding of info theory.
Lempel-Ziv!
Great view!
No irony; it’s more of an infrastructure issue! The US could have a great autonomous driving system with the public transit remaining as is.
I think the brave student was hinting it should be derived now.
Rolling rebuttals, given how minimal the rating changes eventually are, are highly inefficient/ineffective!
