We study the generalization properties of batched predictors, i.e., models tasked with predicting the mean label of a small set (or batch) of examples. The batched prediction paradigm is particularly relevant for models deployed to determine the quality of a group of compounds in preparation for offline testing. By utilizing a suitable generalization of the Rademacher complexity, we prove that batched predictors come with exponentially stronger generalization guarantees as compared to the standard per-sample approach. Surprisingly, the proposed bound holds independently of overparametrization. Our theoretical insights are validated experimentally for various tasks, architectures, and applications.

翻译：我们研究了批次预测器的泛化性质，即模型的任务是预测一小批样本的平均标签。批次预测范式对于部署为评估化合物组质量以准备离线测试的模型尤为重要。通过利用Rademacher复杂度的适当推广，我们证明，与标准的逐样本方法相比，批次预测器具有指数级更强的泛化保证。令人惊讶的是，所提出的界限在过参数化的情况下依然成立。我们的理论见解在多种任务、架构和应用中得到了实验验证。