Boltzmann MapReduce: A Partition-Function Reduce for Forkable Sandboxes

arXiv:2607.09689v2 Announce Type: replace Abstract: To leading order under local asymptotic normality (LAN), the confidence density a worker emits over a chunk of size n is a Gibbs--Boltzmann measure exp{-eta E(heta)} whose inverse temperature is the sample size, eta=n. Three consequences are exact in the Gaussian/linear case and first-order otherwise: disjoint chunks carry independent Boltzmann factors, so the MapReduce reduce, read literally, is a partition function Z=intprod_k h_k,dheta whose mode is precision-weighted (inverse-variance) pooling; frequentist consistency is the zero-temperature limit T=1/no0

Source: arXiv cs.AI | 2026-07-16