Causal Representation Learning from Multiple Distributions: A General Setting
In many problems the measured variables are functions of the latent causal variables (e.g., the underlying concepts or objects). For the purpose of making predictions in changing environments or making proper changes to the system, it is helpful to recover the latent causal variables and their causal relations. This problem has been known as causal representation learning. This paper is concerned with a general, completely nonparametric setting of causal representation learning from multiple distributions, without assuming hard interventions behind distribution changes.
На встрече обсудим:
- Что такое causal representation learning
- Как оно может применятся (на примере EEG)
- Параметрический и непараметрический сеттинг и VAE
• Суббота, 13 сентября, 11:00 KZ Time
• Добавить в календарь
• meet.google.com/aeo-oivb-zdp
• Speaker: Ayana Mussabayeva
