Deep neural networks enable the color constancy algorithms to approximate the function for illuminant estimation. However, the image data required for learning the chromaticity of the illumination remains scarce. Autoencoders provide a promising paradigm to exploit the underlying structure of chromaticity of images by learning over large numbers of unlabeled Internet images, so that we can achieve a good illuminant estimation over new images. We introduce a novel color constancy algorithm by auto-encoding a large dataset of images and using the model to estimate the illumination. We use two approaches. In the first, we learn a common representation of images and then fine-tune the model to estimate the illumination and, in the second approach, we combine the two steps into one using a composite objective function to allow us to learn to reconstruct and, at the same time, regress to the illumination.