1. Achille, A., & Soatto, S. (2018a). Emergence of invariance and disentangling in deep representations. Journal of Machine Learning Research (JMLR), 19, 1–34.
2. Achille, A., & Soatto, S. (2018b). Information dropout: Learning optimal representations through noisy computation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(12), 2897–2905.
3. Alemi, A. A., Fischer, I., Dillon, J. V., & Murphy, K. (2016). Deep variational information bottleneck. CoRR arxiv:1612.00410.
4. Amjad, R. A., & Geiger, B. C. (2018). Learning representations for neural network-based classification using the information bottleneck principle. CoRR arxiv:1802.09766.
5. Bassily, R., Moran, S., Nachum, I., Shafer, J., & Yehudayoff, A. (2018). Learners that use little information. In Proceedings of machine learning research, PMLR, (Vol. 83, pp. 25–55).