通过隐空间过滤实现在线预测，无需梯度更新即可自适应变化环境。
LatentTrack: Sequential Weight Generation via Latent Filtering
- 在低维隐空间中做因果贝叶斯滤波，用轻量超网络生成每步模型参数。
- 在Jena气候数据上长期预测，负对数似然和均方误差均优于基线方法。
- 适合动态环境下的在线建模，尤其适用于分布漂移场景的不确定性估计。
我们提出LatentTrack（LT），一种面向非平稳动态下的在线概率预测的序列神经架构。LT在低维隐空间中执行因果贝叶斯滤波，并使用轻量级超网络在每个时间步生成预测模型参数，实现无需逐步梯度更新的恒定时间在线适应。每个时间步，学习到的隐模型预测下一个隐分布，通过新观测进行近似推断更新，形成函数空间中的预测-生成-更新滤波框架。该方法在统一目标下支持结构化（马尔可夫）与非结构化隐动态，基于隐轨迹的蒙特卡洛推断以固定每步开销生成校准的预测混合分布。在Jena气候基准上的长时序在线回归评估中，LT始终以更低的负对数似然和均方误差优于状态序列与静态不确定性感知基线，且校准性能具有竞争力，表明隐条件函数演化是分布漂移下传统隐状态建模的有效替代方案。
原文摘要 · Abstract (English)
We introduce LatentTrack (LT), a sequential neural architecture for online probabilistic prediction under nonstationary dynamics. LT performs causal Bayesian filtering in a low-dimensional latent space and uses a lightweight hypernetwork to generate predictive model parameters at each time step, enabling constant-time online adaptation without per-step gradient updates. At each time step, a learned latent model predicts the next latent distribution, which is updated via amortized inference using new observations, yielding a predict--generate--update filtering framework in function space. The formulation supports both structured (Markovian) and unstructured latent dynamics within a unified objective, while Monte Carlo inference over latent trajectories produces calibrated predictive mixtures with fixed per-step cost. Evaluated on long-horizon online regression using the Jena Climate benchmark, LT consistently achieves lower negative log-likelihood and mean squared error than stateful sequential and static uncertainty-aware baselines, with competitive calibration, demonstrating that latent-conditioned function evolution is an effective alternative to traditional latent-state modeling under distribution shift.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。