Greedy Byte-Pair Encoding Achieves 0.391 of the Optimum, Past the One-Third Barrier for Packing-Based Analyses

원문 초록

Byte-Pair Encoding (BPE) builds most language-model tokenisers by repeatedly merging a most frequent adjacent pair of symbols. How much shortening can this greedy rule lose against the best $k$ merges? Kozma and Voderholzer proved that greedy achieves at least one third of the optimal shortening; the best known upper bound is $(1-e^{-2})/2\approx 0.432$. We show that one third is a barrier for packing-based analyses, which see the optimum only through a pair packing, and we prove that greedy achieves at least $0.391$ of the optimum on every input, with any tie-breaking. The key idea is rule determinism: all copies of a rule of the optimum spell the same letters, so when one greedy replacement destroys three of the optimum's merge points, half a unit can be refunded on each side. A weaker bound, $0.374$, has a short proof that needs no computer; $0.391$ adds a certificate in exact arithmetic. We also show that the worst-case ratio is exactly $3/4$ for two merges and at most $7/12$ for three.