发表机构
OranAI; OranAI Ltd.; Northeastern University（奥兰AI; 奥兰AI有限公司; 东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出可微高斯动力学（DGD），通过高斯混合表示、可微聚合和反馈循环，从聚合观测中学习集体响应分布，在多个数据集上显著降低预测误差，验证了学习群体表示及反馈过程的价值。
AI 中文摘要
集体响应取决于个体差异、接触机会和累积经验。从聚合计数中学习其动力学，需要将群体的响应分布与当前观测和未来行为联系起来。我们提出了可微高斯动力学（DGD），通过三个组成部分学习这种联系：一个表示异质性响应倾向的高斯混合模型、接触强度和行为概率的可微聚合，以及更新后续响应的反馈循环。重参数化积分和时间循环使得聚合预测误差能够联合训练分布、观测函数和反馈参数。在KuaiRand-Pure和Online Retail II的四个窗口上，DGD的联合行为负对数似然低于带有联合行为头的DeepAR改编版本。在Retail 2010中，其单日行为计数MAE为4.71，而该改编版本为6.88。学习分布相对于固定高斯在KuaiRand标准推荐窗口中将行为负对数似然降低了10.82%；在受控实验中，移除反馈动力学使联合KL从0.0340上升到0.2577。这些结果证明了从聚合观测中学习群体表示及其反馈过程的价值。代码可在https://github.com/OranAi-Ltd/oransim获取。
英文摘要
Collective responses depend on individual differences, contact opportunities, and accumulated experience. Learning their dynamics from aggregate counts requires connecting a population's response distribution to both current observations and future behavior. We introduce Differentiable Gaussian Dynamics (DGD), which learns this connection through three components: a Gaussian mixture representing heterogeneous response propensities, differentiable aggregation of contact intensity and behavioral probabilities, and feedback recurrence that updates subsequent responses. Reparameterized integration and temporal recurrence let aggregate prediction errors jointly train the distribution, observation functions, and feedback parameters. On four windows from KuaiRand-Pure and Online Retail II, DGD achieves lower joint behavioral negative log-likelihood than a DeepAR adaptation with a joint-behavior head. In Retail 2010, its one-day behavioral-count MAE is 4.71 versus 6.88 for this adaptation. Learning the distribution reduces behavioral negative log-likelihood by 10.82% relative to a fixed Gaussian in KuaiRand's standard-recommendation window; removing feedback dynamics raises joint KL from 0.0340 to 0.2577 in a controlled experiment. These results establish the value of learning population representations and their feedback process from aggregate observations. Code is available at https://github.com/OranAi-Ltd/oransim.
Comments23 pages, 2 figures. Revised manuscript and updated references. Code: https://github.com/OranAi-Ltd/oransim
