We study poverty minimization via direct transfers, framing this as a statistical learning problem while retaining the information constraints faced by real-world programs. Using nationally representative household consumption surveys from 23 countries that together account for 50% of the world’s poor, we estimate that reducing the poverty rate to 1% (from a baseline of 12% at the time of last survey) would cost $170B nominal per year. This is 5.5 times the corresponding reduction in the aggregate poverty gap, but only 19% of the cost of universal basic income. Extrapolated globally, the results correspond to a cost of (approximately) ending extreme poverty of roughly 0.3% of global GDP.