arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.03329cs.LGstat.ME
收藏

超越欧几里得范式的统计有意义几何(SMG)及其在生成式人工智能中的应用

Statistically Meaningful Geometry (SMG) Beyond the Euclidean Paradigm, with Application to Generative AI

Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);AMSS Center for Forecasting Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院预测科学研究中心);Beijing Institute of Mathematical Sciences and Applications (BIMSA)(北京国际数学研究中心);Department of Statistics, London School of Economics and Political Science(伦敦政治经济学院统计系);Department of Statistics and Data Science, Tsinghua University(清华大学统计与数据科学系);Paula and Gregory Chow Institute for the Studies in Economics, Xiamen University(厦门大学经济研究所(保拉和格雷戈里·周研究所));Yau Mathematical Sciences Center, Tsinghua University(清华大学丘成桐数学科学中心)

Bing Cheng, Yi-Shuai Niu, Howell Tong, Shing-Tung Yau

AI总结:

研究大规模过参数化模型问题,引入SMG框架,将确定性参数模型提升到无限维非参数Orlicz统计流形,建立双重推理范式,证明可抑制生成幻觉并消除灾难性遗忘。

摘要:

传统均匀收敛界和经验风险最小化在大规模过参数化模型中失效。我们引入统计有意义几何(SMG)框架,将确定性参数模型提升到无限维非参数Orlicz统计流形。建立双重推理范式,证明可抑制生成幻觉并消除灾难性遗忘,用无坐标拓扑约束取代经验微调启发式方法。

英文摘要:

Conventional uniform convergence bounds and empirical risk minimization break down in massive over-parameterized models, such as large language transformers and biological sequence networks. With near-infinite unconstrained internal degrees of freedom, their optimization landscapes develop flat vertical gauge valleys, rendering classical generalization metrics vacuous and inducing severe pathologies, specifically generative hallucination and catastrophic forgetting. We introduce the Statistically Meaningful Geometry (SMG) framework, an information-geometric paradigm lifting deterministic parametric models into infinite-dimensional non-parametric Orlicz statistical manifolds. Modeling the total state space as a differential fiber bundle ($\mathcal{M}, \mathcal{B}, π, \mathcal{V}, \mathcal{H}, ω$), we establish a Two-Fold Inference Paradigm. We formalize an Ehresmann connection 1-form $ω$ as a dynamic geometric filter that strips away vertical gauge noise (Structural Internal Directions, or SID) and isolates learning trajectories along the strictly non-degenerate horizontal distribution (Statistical Variational Directions, or SVD$χ$). We prove that under connection-filtered pre-training, out-of-distribution predictive variance is strictly upper-bounded by the finite diameter of the identifiable quotient base manifold $\mathcal{B}$, establishing a hard geometric containment of generative hallucinations. By projecting downstream updates onto the orthogonal complement of the historical horizontal carriage, we formalize the SMG Sequential Adaptation Flow, proving the total non-asymptotic elimination of catastrophic forgetting. SMG replaces empirical fine-tuning heuristics with coordinate-free topological constraints, bridging advanced differential geometry with structural reliability in AI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑