The electronic density of states (DOS) provides information regarding the distribution of electronic energy levels in a material, and can be used to approximate its optical and electronic properties and therefore guide computational materials design. Given its usefulness and relative simplicity, it has been one of the first electronic properties used as a target for machine-learning approaches going beyond interatomic potentials. A subtle but important point, well appreciated in the condensed matter community but usually overlooked in the construction of data-driven models, is that for bulk configurations the absolute energy reference of single-particle energy levels is ill-defined. Only energy differences matter, and quantities derived from the DOS are typically independent of the absolute alignment. We introduce an adaptive scheme that optimizes the energy reference of each structure as part of the training process and show that it consistently improves the quality of machine-learning models compared to traditional choices of energy reference for different classes of materials and different model architectures. On a practical level, we trace the improved performance to the ability of this self-aligning scheme to match the most prominent features in the DOS. More broadly, we believe that this paper highlights the importance of incorporating insights on the nature of the physical target into the definition of the architecture and of the appropriate figures of merit for machine-learning models, translating into better transferability and overall performance.