Note: a difference definition provided in Yoshua Bengio’s blog post scaling-in-the-service-of-reasoning-model-based-ml:
A causal model can be understood as an exponentially large family of distributions indexed by a choice of intervention, …
How can this be useful? Compared to Peter Spirtes’ one (i.e., a stat model and a causal graph)
My thought: I don’t think I should read too much into this because the entire article and paragraph treat the subject at a high level, there isn’t much robust reasoning behind it.
Next question based on this remark: “The reason why GFlowNet is the ideal tool for the job is it is good at representing distributions and sampling over graphs.”
How does GFlowNet represent distributions and sampling over graphs?
Gang Fang's Blog 
Leave a comment