DoPr 解决了训练和部署性能不一致的痛点，做自回归模型、流生成或机器人学习的团队可以直接尝试这个即插即用优化器，可能会发现验证损失没变但实际效果提升。
论文提出一种名为双预处理（DoPr）的新优化范式，专门解决深度学习模型在部署时因自身预测滚动（如自回归语言模型、流生成模型、机器人策略学习）导致的误差累积问题。DoPr 结合梯度预处理（如 Adam、Muon）和激活预处理（如 KFAC），能直接提升下游任务性能（如成功率、生成质量），而不一定改善验证损失。这挑战了传统以验证损失为优化目标的评估方式，为训练-测试不匹配问题提供了新的优化维度。实验表明，DoPr 在多种测试时反馈（TTF）场景中作为即插即用模块有效。
Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss
Many modern applications of deep learning involve training a neural network via a one-step prediction loss (e.g., $L^2$ regression, cross-entropy), but deploy the network by rolling out along its own predictions. Key examples include autoregressive language modeling, flow-based generative modeling, and robot policy learning. It is well-documented that these settings induce a phenomenon we call test-time feedback (TTF): the mismatch between the training/validation loss and downstream metrics of interest, such as task success rate and generation quality, which grows with task length. While data curation, architecture, and objective design have been proposed to combat train-test shift in TTF settings, this paper proposes optimization as a new design axis to mitigate error accumulation. Specifically, we introduce a new optimization paradigm called double-preconditioning (DoPr) uniquely tailored to the challenges of TTF. DoPr combines gradient-wise preconditioning, as in Adam and Muon, with activation-wise preconditioning (AP), such as in KFAC. We show that the addition of AP yields a drop-in intervention for increasing downstream model performance across a range of TTF settings. Interestingly, these gains in test-time performance do not consistently accompany improvements in validation loss, opening new questions about how to properly evaluate models trained with one-step supervised objectives.