factual
The Search Problem Makes Ideal Bayesian Inference Intractable
Ideal Bayesian inference is computationally impossible at scale because with a large hypothesis space you would have to test each hypothesis separately to find which best generated the data—the search problem—and this remains unsolved in statistics, AI, and developmental psychology; yet children clearly solve it, and active intervention may be part of how they do so.
factualpending
Speaker
Alison GopnikEvidence Quote
“if you have a big space of hypothesis, that's just gonna take forever because you're gonna have to try each one of the hypotheses separately. It's called the search problem. And nobody's really quite solved that problem”
Created: 6/13/2026, 12:24:35 AM
Your notes
Loading notes...