Doeblin锚定对比图:学习马尔可夫转移核
A Doeblin-Anchored Contrastive Chart for Learning Markov Transition Kernels
AI总结:
提出一种基于Doeblin锚定的对比坐标框架,通过对比目标学习有效的马尔可夫转移核,并引入可测马尔可夫化算子保证核有效性,实现非参数收敛率与有限时域误差界。
摘要:
学习马尔可夫转移模型不仅仅是条件密度估计:学习到的对象必须是一个有效的转移核,才能在后续动力学中迭代。本文介绍了一种Doeblin锚定对比图,这是一个从统计到动力学的坐标框架,用于从对比目标学习转移核。给定一个重启律和一个锚定强度,该图将目标转移与重启律混合。得到的锚定核同时是一个Doeblin小化马尔可夫核、一个二元对比实验中的正条件律,以及原始转移律的一个显式可逆坐标。我们证明了锚定对比风险识别锚定转移密度,并将超额风险校准为密度误差。由于学习得分的反演可能产生有符号或未归一化的对象,我们引入了一个可测马尔可夫化算子,在保持积分$L^1$精度(最多一个常数因子)的同时恢复核有效性。Oracle不等式和Hölder-ReLU逼近界给出了独立转移对的非参数速率。对于平稳几何$\beta$-混合轨迹,一个保守的稀疏化与耦合扩展以有效样本量提供了相同的重建接口。在显式覆盖下,占用加权扰动界将一步核误差转化为有限时域边际、路径律和占用测度误差。
英文摘要:
Learning a Markov transition model is not merely conditional density estimation: the learned object must be a valid transition kernel before it is iterated in downstream dynamics. This paper introduces a Doeblin-anchored contrastive chart, a statistical-to-dynamical coordinate framework for learning transition kernels from contrastive objectives. Given a restart law and an anchor strength, the chart mixes the target transition with the restart law. The resulting anchored kernel is simultaneously a Doeblin-minorized Markov kernel, the positive conditional law in a binary contrastive experiment, and an explicitly invertible coordinate for the original transition law. We prove that the anchored contrastive risk identifies the anchored transition density and calibrates excess risk to density error. Since inversion of a learned score may produce a signed or unnormalized object, we introduce a measurable Markovization operator that restores kernel validity while preserving integrated $L^1$ accuracy up to a constant factor. Oracle inequalities and Hölder--ReLU approximation bounds yield nonparametric rates for independent transition pairs. For stationary geometrically $β$-mixing trajectories, a conservative thinning-and-coupling extension yields the same reconstruction interface with an effective sample size. Occupancy-weighted perturbation bounds transfer one-step kernel error to finite-horizon marginal, path-law, and occupation-measure errors under explicit coverage.
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。