提出可自适应切换的在线跟踪框架，提升非平稳环境下的预测性能。
Policy-Controlled Generalized Share: A General Framework with a Transformer Instantiation for Strictly Online Switching-Oracle Tracking
- 用因果Transformer控制更新策略，动态调整权重但不改变已决策。
- 在7类非平稳数据中均实现最低动态误差，专家池越大优势越明显。
- 适合需要频繁切换最优策略的实时预测场景，如能源管理、金融交易。
静态后悔基准在非平稳环境下往往不适用，因最优专家可能频繁切换。本文提出策略可控广义共享（PCGS）框架，固定广义共享递推关系，允许损失后更新策略自适应变化。主要实例PCGS-TF采用因果Transformer作为更新控制器：每轮结束后根据损失向量输出控制信号，将w_t映射到w_{t+1}，而不修改已确定的w_t。在合理更新控制下，获得对任意时变学习率的路径加权后悔保证；在常学习率下，对最多有S次切换的专家路径提供标准动态后悔保证。实验表明，在包含7种非平稳结构的合成数据集上，PCGS-TF在所有情况下均达到最低平均动态后悔，且专家池越大其优势越显著。在家庭用电数据集上的复现结果也显示，当S=5、10、20时，其归一化动态后悔最低。
原文摘要 · Abstract (English)
Static regret to a single expert is often the wrong target for strictly online prediction under non-stationarity, where the best expert may switch repeatedly over time. We study Policy-Controlled Generalized Share (PCGS), a general strictly online framework in which the generalized-share recursion is fixed while the post-loss update controls are allowed to vary adaptively. Its principal instantiation in this paper is PCGS-TF, which uses a causal Transformer as an update controller: after round t finishes and the loss vector is observed, the Transformer outputs the controls that map w_t to w_{t+1} without altering the already committed decision w_t. Under admissible post-loss update controls, we obtain a pathwise weighted regret guarantee for general time-varying learning rates, and a standard dynamic-regret guarantee against any expert path with at most S switches under the constant-learning-rate specialization. Empirically, on a controlled synthetic suite with exact dynamic-programming switching-oracle evaluation, PCGS-TF attains the lowest mean dynamic regret in all seven non-stationary families, with its advantage increasing for larger expert pools. On a reproduced household-electricity benchmark, PCGS-TF also achieves the lowest normalized dynamic regret for S = 5, 10, and 20.
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。