← 研踪 PaperTrailarXiv:2609.40290 · v3
Orbits as Strong Models: Kolmogorov Structure Function under Symmetry
首次提交 2026-10-01 01:49
版本更新 2026-11-18 08:15
雷达观测 2026-11-19 19:08
摘要
Strong models in algorithmic statistics are essentially the cells of simple partitions of . We study the partitions that come from symmetry, the orbit partitions of groups acting on strings, and the structure function they induce. A set is a cell of such a partition exactly when its setwise stabiliser acts transitively on it, so is Kolmogorov's structure function restricted to -homogeneous sets. For the full symmetric group this recovers all models and exactly the strong ones. For the cells are the linearly homogeneous sets, lies in a band between and with both edges attained, and some stochastic normal strings have simple structure that is invisible to linear symmetry. Writing each permutation group as a Burnside-ring type with a placement, we show that any space of symmetry hypotheses small enough to search is small enough to miss simple structure. Finally we cast the search for orbit models as value estimation on subgroup lattices, with computable bounds, certified training targets and a lattice version of Monte Carlo tree search.
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。
v3 · 2026-11-18 08:15 · 最新观测版本
Orbits as Strong Models: Kolmogorov Structure Function under Symmetry
Strong models in algorithmic statistics are essentially the cells of simple partitions of . We study the partitions that come from symmetry, the orbit partitions of groups acting on strings, and the structure function they induce. A set is a cell of such a partition exactly when its setwise stabiliser acts transitively on it, so is Kolmogorov's structure function restricted to -homogeneous sets. For the full symmetric group this recovers all models and exactly the strong ones. For the cells are the linearly homogeneous sets, lies in a band between and with both edges attained, and some stochastic normal strings have simple structure that is invisible to linear symmetry. Writing each permutation group as a Burnside-ring type with a placement, we show that any space of symmetry hypotheses small enough to search is small enough to miss simple structure. Finally we cast the search for orbit models as value estimation on subgroup lattices, with computable bounds, certified training targets and a lattice version of Monte Carlo tree search.
查看此版本解读 →查看此版本原文 ↗