Fast AI aggregation in social learning has no robustly improving training weights, but slow and local aggregators do improve learning across environments.
For the former case, we have ∆1(ρ, α, β, h, π)−∆ 0(h, π) = ¯∆1(ρ, α, β, h, π)−∆ 0(h, π)<max n α, hπ2+π hπ2+2π+h o − hπ2+π hπ2+2π+h = 0
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
econ.TH 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
How AI Aggregation Affects Knowledge
Fast AI aggregation in social learning has no robustly improving training weights, but slow and local aggregators do improve learning across environments.