← 研踪 PaperTrailarXiv:2611.21285 · v1
The Price of Not Planning: Parallel Sampling Depth Peaks at the Reconstruction Threshold
首次提交 2026-11-16 23:54
版本更新 2026-11-16 23:54
雷达观测 2026-11-17 16:10
摘要
Masked diffusion models sample the tokens of one round independently. Planned decoders first generate a coarse plan, then fill in the tokens in parallel. We ask when a plan saves rounds, how many it saves, and how fine it must be. We study this on broadcast trees: the leaves are the tokens, the internal nodes are the plan, and the edge correlation sets how strongly tokens depend on the plan. Errors are measured by the forward Kullback-Leibler divergence , and the lower bounds hold for every deterministic value-adaptive rule, also with learned conditionals. We show that a decoder without the plan needs of order rounds below the reconstruction threshold, where rises to at the threshold, and that the exponent stays below above it (binary channel: ). With the plan, rounds suffice. In the binary model below the threshold, a plan with units of tokens needs of order rounds, so it gives logarithmic depth exactly when is logarithmic. A plan therefore helps most near the threshold, and only if its units are small. Exact divergence computations in the Gaussian model with up to leaves confirm these exponents below the threshold.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-16 23:54 · 最新观测版本
The Price of Not Planning: Parallel Sampling Depth Peaks at the Reconstruction Threshold
Masked diffusion models sample the tokens of one round independently. Planned decoders first generate a coarse plan, then fill in the tokens in parallel. We ask when a plan saves rounds, how many it saves, and how fine it must be. We study this on broadcast trees: the leaves are the tokens, the internal nodes are the plan, and the edge correlation sets how strongly tokens depend on the plan. Errors are measured by the forward Kullback-Leibler divergence , and the lower bounds hold for every deterministic value-adaptive rule, also with learned conditionals. We show that a decoder without the plan needs of order rounds below the reconstruction threshold, where rises to at the threshold, and that the exponent stays below above it (binary channel: ). With the plan, rounds suffice. In the binary model below the threshold, a plan with units of tokens needs of order rounds, so it gives logarithmic depth exactly when is logarithmic. A plan therefore helps most near the threshold, and only if its units are small. Exact divergence computations in the Gaussian model with up to leaves confirm these exponents below the threshold.
查看此版本解读 →查看此版本原文 ↗